From a308356d5c7c165bc4c9f8732f1fe920dcd4b67a Mon Sep 17 00:00:00 2001
From: nichongjia-2007 <nichongjia@gmail.com>
Date: 星期一, 03 七月 2023 15:02:11 +0800
Subject: [PATCH] Merge branch 'main' of https://github.com/alibaba-damo-academy/FunASR
---
funasr/build_utils/build_asr_model.py | 68 +
funasr/modules/embedding.py | 7
funasr/runtime/python/websocket/wss_client_asr.py | 5
funasr/models/e2e_asr_bat.py | 496 +++++++++
funasr/runtime/python/websocket/README.md | 2
funasr/tasks/asr.py | 138 ++
funasr/runtime/docs/SDK_advanced_guide_offline.md | 259 ++++
funasr/runtime/docs/SDK_advanced_guide_offline_zh.md | 11
funasr/runtime/readme_cn.md | 22
funasr/runtime/readme.md | 2
README.md | 9
funasr/runtime/docs/images/html.png | 0
funasr/runtime/docs/aliyun_server_tutorial.md | 12
/dev/null | 327 ------
funasr/runtime/docs/docker_offline_cpu_zh_lists | 8
funasr/runtime/docs/SDK_tutorial.md | 6
funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh | 1450 ++++++++++++++++++++++++++
funasr/models/predictor/cif.py | 127 ++
funasr/runtime/docs/SDK_tutorial_zh.md | 188 +++
funasr/bin/asr_inference_launch.py | 2
funasr/runtime/run_server.sh | 25
funasr/models/e2e_asr_transducer.py | 23
22 files changed, 2,796 insertions(+), 391 deletions(-)
diff --git a/README.md b/README.md
index 26cf940..3969ac1 100644
--- a/README.md
+++ b/README.md
@@ -20,9 +20,18 @@
| [**M2MET2.0 Challenge**](https://github.com/alibaba-damo-academy/FunASR#multi-channel-multi-party-meeting-transcription-20-m2met20-challenge)
## What's new:
+
+### FunASR runtime-SDK
+
+- 2023.07.02:
+We have release the FunASR runtime-SDK-0.1.0, file transcription service (Mandarin) is now supported ([ZH](funasr/runtime/readme_cn.md)/[EN](funasr/runtime/readme.md))
+
### Multi-Channel Multi-Party Meeting Transcription 2.0 (M2MeT2.0) Challenge
+
We are pleased to announce that the M2MeT2.0 challenge has been accepted by the ASRU 2023 challenge special session. The registration is now open. The baseline system is conducted on FunASR and is provided as a receipe of AliMeeting corpus. For more details you can see the guidence of M2MET2.0 ([CN](https://alibaba-damo-academy.github.io/FunASR/m2met2_cn/index.html)/[EN](https://alibaba-damo-academy.github.io/FunASR/m2met2/index.html)).
+
### Release notes
+
For the release notes, please ref to [news](https://github.com/alibaba-damo-academy/FunASR/releases)
## Highlights
diff --git a/funasr/bin/asr_inference_launch.py b/funasr/bin/asr_inference_launch.py
index 37a5fe4..81513ae 100644
--- a/funasr/bin/asr_inference_launch.py
+++ b/funasr/bin/asr_inference_launch.py
@@ -1604,6 +1604,8 @@
return inference_mfcca(**kwargs)
elif mode == "rnnt":
return inference_transducer(**kwargs)
+ elif mode == "bat":
+ return inference_transducer(**kwargs)
elif mode == "sa_asr":
return inference_sa_asr(**kwargs)
else:
diff --git a/funasr/build_utils/build_asr_model.py b/funasr/build_utils/build_asr_model.py
index a76b204..6606d30 100644
--- a/funasr/build_utils/build_asr_model.py
+++ b/funasr/build_utils/build_asr_model.py
@@ -26,6 +26,7 @@
from funasr.models.e2e_asr_mfcca import MFCCA
from funasr.models.e2e_asr_transducer import TransducerModel, UnifiedTransducerModel
+from funasr.models.e2e_asr_bat import BATModel
from funasr.models.e2e_sa_asr import SAASRModel
from funasr.models.e2e_asr_paraformer import Paraformer, ParaformerOnline, ParaformerBert, BiCifParaformer, ContextualParaformer
@@ -46,7 +47,7 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.models.frontend.windowing import SlidingWindow
from funasr.models.joint_net.joint_network import JointNetwork
-from funasr.models.predictor.cif import CifPredictor, CifPredictorV2, CifPredictorV3
+from funasr.models.predictor.cif import CifPredictor, CifPredictorV2, CifPredictorV3, BATPredictor
from funasr.models.specaug.specaug import SpecAug
from funasr.models.specaug.specaug import SpecAugLFR
from funasr.modules.subsampling import Conv1dSubsampling
@@ -99,7 +100,7 @@
rnnt=TransducerModel,
rnnt_unified=UnifiedTransducerModel,
sa_asr=SAASRModel,
-
+ bat=BATModel,
),
default="asr",
)
@@ -188,6 +189,7 @@
ctc_predictor=None,
cif_predictor_v2=CifPredictorV2,
cif_predictor_v3=CifPredictorV3,
+ bat_predictor=BATPredictor,
),
default="cif_predictor",
optional=True,
@@ -313,12 +315,15 @@
encoder = encoder_class(input_size=input_size, **args.encoder_conf)
# decoder
- decoder_class = decoder_choices.get_class(args.decoder)
- decoder = decoder_class(
- vocab_size=vocab_size,
- encoder_output_size=encoder.output_size(),
- **args.decoder_conf,
- )
+ if hasattr(args, "decoder") and args.decoder is not None:
+ decoder_class = decoder_choices.get_class(args.decoder)
+ decoder = decoder_class(
+ vocab_size=vocab_size,
+ encoder_output_size=encoder.output_size(),
+ **args.decoder_conf,
+ )
+ else:
+ decoder = None
# ctc
ctc = CTC(
@@ -463,6 +468,53 @@
joint_network=joint_network,
**args.model_conf,
)
+ elif args.model == "bat":
+ # 5. Decoder
+ encoder_output_size = encoder.output_size()
+
+ rnnt_decoder_class = rnnt_decoder_choices.get_class(args.rnnt_decoder)
+ decoder = rnnt_decoder_class(
+ vocab_size,
+ **args.rnnt_decoder_conf,
+ )
+ decoder_output_size = decoder.output_size
+
+ if getattr(args, "decoder", None) is not None:
+ att_decoder_class = decoder_choices.get_class(args.decoder)
+
+ att_decoder = att_decoder_class(
+ vocab_size=vocab_size,
+ encoder_output_size=encoder_output_size,
+ **args.decoder_conf,
+ )
+ else:
+ att_decoder = None
+ # 6. Joint Network
+ joint_network = JointNetwork(
+ vocab_size,
+ encoder_output_size,
+ decoder_output_size,
+ **args.joint_network_conf,
+ )
+
+ predictor_class = predictor_choices.get_class(args.predictor)
+ predictor = predictor_class(**args.predictor_conf)
+
+ model_class = model_choices.get_class(args.model)
+ # 7. Build model
+ model = model_class(
+ vocab_size=vocab_size,
+ token_list=token_list,
+ frontend=frontend,
+ specaug=specaug,
+ normalize=normalize,
+ encoder=encoder,
+ decoder=decoder,
+ att_decoder=att_decoder,
+ joint_network=joint_network,
+ predictor=predictor,
+ **args.model_conf,
+ )
elif args.model == "sa_asr":
asr_encoder_class = asr_encoder_choices.get_class(args.asr_encoder)
asr_encoder = asr_encoder_class(input_size=input_size, **args.asr_encoder_conf)
diff --git a/funasr/models/e2e_asr_bat.py b/funasr/models/e2e_asr_bat.py
new file mode 100644
index 0000000..9627292
--- /dev/null
+++ b/funasr/models/e2e_asr_bat.py
@@ -0,0 +1,496 @@
+"""Boundary Aware Transducer (BAT) model."""
+
+import logging
+from contextlib import contextmanager
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from packaging.version import parse as V
+from funasr.losses.label_smoothing_loss import (
+ LabelSmoothingLoss, # noqa: H301
+)
+from funasr.models.frontend.abs_frontend import AbsFrontend
+from funasr.models.specaug.abs_specaug import AbsSpecAug
+from funasr.models.decoder.rnnt_decoder import RNNTDecoder
+from funasr.models.decoder.abs_decoder import AbsDecoder as AbsAttDecoder
+from funasr.models.encoder.abs_encoder import AbsEncoder
+from funasr.models.joint_net.joint_network import JointNetwork
+from funasr.modules.nets_utils import get_transducer_task_io
+from funasr.modules.nets_utils import th_accuracy
+from funasr.modules.nets_utils import make_pad_mask
+from funasr.modules.add_sos_eos import add_sos_eos
+from funasr.layers.abs_normalize import AbsNormalize
+from funasr.torch_utils.device_funcs import force_gatherable
+from funasr.models.base_model import FunASRModel
+
+if V(torch.__version__) >= V("1.6.0"):
+ from torch.cuda.amp import autocast
+else:
+
+ @contextmanager
+ def autocast(enabled=True):
+ yield
+
+
+class BATModel(FunASRModel):
+ """BATModel module definition.
+
+ Args:
+ vocab_size: Size of complete vocabulary (w/ EOS and blank included).
+ token_list: List of token
+ frontend: Frontend module.
+ specaug: SpecAugment module.
+ normalize: Normalization module.
+ encoder: Encoder module.
+ decoder: Decoder module.
+ joint_network: Joint Network module.
+ transducer_weight: Weight of the Transducer loss.
+ fastemit_lambda: FastEmit lambda value.
+ auxiliary_ctc_weight: Weight of auxiliary CTC loss.
+ auxiliary_ctc_dropout_rate: Dropout rate for auxiliary CTC loss inputs.
+ auxiliary_lm_loss_weight: Weight of auxiliary LM loss.
+ auxiliary_lm_loss_smoothing: Smoothing rate for LM loss' label smoothing.
+ ignore_id: Initial padding ID.
+ sym_space: Space symbol.
+ sym_blank: Blank Symbol
+ report_cer: Whether to report Character Error Rate during validation.
+ report_wer: Whether to report Word Error Rate during validation.
+ extract_feats_in_collect_stats: Whether to use extract_feats stats collection.
+
+ """
+
+ def __init__(
+ self,
+ vocab_size: int,
+ token_list: Union[Tuple[str, ...], List[str]],
+ frontend: Optional[AbsFrontend],
+ specaug: Optional[AbsSpecAug],
+ normalize: Optional[AbsNormalize],
+ encoder: AbsEncoder,
+ decoder: RNNTDecoder,
+ joint_network: JointNetwork,
+ att_decoder: Optional[AbsAttDecoder] = None,
+ predictor = None,
+ transducer_weight: float = 1.0,
+ predictor_weight: float = 1.0,
+ cif_weight: float = 1.0,
+ fastemit_lambda: float = 0.0,
+ auxiliary_ctc_weight: float = 0.0,
+ auxiliary_ctc_dropout_rate: float = 0.0,
+ auxiliary_lm_loss_weight: float = 0.0,
+ auxiliary_lm_loss_smoothing: float = 0.0,
+ ignore_id: int = -1,
+ sym_space: str = "<space>",
+ sym_blank: str = "<blank>",
+ report_cer: bool = True,
+ report_wer: bool = True,
+ extract_feats_in_collect_stats: bool = True,
+ lsm_weight: float = 0.0,
+ length_normalized_loss: bool = False,
+ r_d: int = 5,
+ r_u: int = 5,
+ ) -> None:
+ """Construct an BATModel object."""
+ super().__init__()
+
+ # The following labels ID are reserved: 0 (blank) and vocab_size - 1 (sos/eos)
+ self.blank_id = 0
+ self.vocab_size = vocab_size
+ self.ignore_id = ignore_id
+ self.token_list = token_list.copy()
+
+ self.sym_space = sym_space
+ self.sym_blank = sym_blank
+
+ self.frontend = frontend
+ self.specaug = specaug
+ self.normalize = normalize
+
+ self.encoder = encoder
+ self.decoder = decoder
+ self.joint_network = joint_network
+
+ self.criterion_transducer = None
+ self.error_calculator = None
+
+ self.use_auxiliary_ctc = auxiliary_ctc_weight > 0
+ self.use_auxiliary_lm_loss = auxiliary_lm_loss_weight > 0
+
+ if self.use_auxiliary_ctc:
+ self.ctc_lin = torch.nn.Linear(encoder.output_size(), vocab_size)
+ self.ctc_dropout_rate = auxiliary_ctc_dropout_rate
+
+ if self.use_auxiliary_lm_loss:
+ self.lm_lin = torch.nn.Linear(decoder.output_size, vocab_size)
+ self.lm_loss_smoothing = auxiliary_lm_loss_smoothing
+
+ self.transducer_weight = transducer_weight
+ self.fastemit_lambda = fastemit_lambda
+
+ self.auxiliary_ctc_weight = auxiliary_ctc_weight
+ self.auxiliary_lm_loss_weight = auxiliary_lm_loss_weight
+
+ self.report_cer = report_cer
+ self.report_wer = report_wer
+
+ self.extract_feats_in_collect_stats = extract_feats_in_collect_stats
+
+ self.criterion_pre = torch.nn.L1Loss()
+ self.predictor_weight = predictor_weight
+ self.predictor = predictor
+
+ self.cif_weight = cif_weight
+ if self.cif_weight > 0:
+ self.cif_output_layer = torch.nn.Linear(encoder.output_size(), vocab_size)
+ self.criterion_cif = LabelSmoothingLoss(
+ size=vocab_size,
+ padding_idx=ignore_id,
+ smoothing=lsm_weight,
+ normalize_length=length_normalized_loss,
+ )
+ self.r_d = r_d
+ self.r_u = r_u
+
+ def forward(
+ self,
+ speech: torch.Tensor,
+ speech_lengths: torch.Tensor,
+ text: torch.Tensor,
+ text_lengths: torch.Tensor,
+ **kwargs,
+ ) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]:
+ """Forward architecture and compute loss(es).
+
+ Args:
+ speech: Speech sequences. (B, S)
+ speech_lengths: Speech sequences lengths. (B,)
+ text: Label ID sequences. (B, L)
+ text_lengths: Label ID sequences lengths. (B,)
+ kwargs: Contains "utts_id".
+
+ Return:
+ loss: Main loss value.
+ stats: Task statistics.
+ weight: Task weights.
+
+ """
+ assert text_lengths.dim() == 1, text_lengths.shape
+ assert (
+ speech.shape[0]
+ == speech_lengths.shape[0]
+ == text.shape[0]
+ == text_lengths.shape[0]
+ ), (speech.shape, speech_lengths.shape, text.shape, text_lengths.shape)
+
+ batch_size = speech.shape[0]
+ text = text[:, : text_lengths.max()]
+
+ # 1. Encoder
+ encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
+ if hasattr(self.encoder, 'overlap_chunk_cls') and self.encoder.overlap_chunk_cls is not None:
+ encoder_out, encoder_out_lens = self.encoder.overlap_chunk_cls.remove_chunk(encoder_out, encoder_out_lens,
+ chunk_outs=None)
+
+ encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(encoder_out.device)
+ # 2. Transducer-related I/O preparation
+ decoder_in, target, t_len, u_len = get_transducer_task_io(
+ text,
+ encoder_out_lens,
+ ignore_id=self.ignore_id,
+ )
+
+ # 3. Decoder
+ self.decoder.set_device(encoder_out.device)
+ decoder_out = self.decoder(decoder_in, u_len)
+
+ pre_acoustic_embeds, pre_token_length, _, pre_peak_index = self.predictor(encoder_out, text, encoder_out_mask, ignore_id=self.ignore_id)
+ loss_pre = self.criterion_pre(text_lengths.type_as(pre_token_length), pre_token_length)
+
+ if self.cif_weight > 0.0:
+ cif_predict = self.cif_output_layer(pre_acoustic_embeds)
+ loss_cif = self.criterion_cif(cif_predict, text)
+ else:
+ loss_cif = 0.0
+
+ # 5. Losses
+ boundary = torch.zeros((encoder_out.size(0), 4), dtype=torch.int64, device=encoder_out.device)
+ boundary[:, 2] = u_len.long().detach()
+ boundary[:, 3] = t_len.long().detach()
+
+ pre_peak_index = torch.floor(pre_peak_index).long()
+ s_begin = pre_peak_index - self.r_d
+
+ T = encoder_out.size(1)
+ B = encoder_out.size(0)
+ U = decoder_out.size(1)
+
+ mask = torch.arange(0, T, device=encoder_out.device).reshape(1, T).expand(B, T)
+ mask = mask <= boundary[:, 3].reshape(B, 1) - 1
+
+ s_begin_padding = boundary[:, 2].reshape(B, 1) - (self.r_u+self.r_d) + 1
+ # handle the cases where `len(symbols) < s_range`
+ s_begin_padding = torch.clamp(s_begin_padding, min=0)
+
+ s_begin = torch.where(mask, s_begin, s_begin_padding)
+
+ mask2 = s_begin < boundary[:, 2].reshape(B, 1) - (self.r_u+self.r_d) + 1
+
+ s_begin = torch.where(mask2, s_begin, boundary[:, 2].reshape(B, 1) - (self.r_u+self.r_d) + 1)
+
+ s_begin = torch.clamp(s_begin, min=0)
+
+ ranges = s_begin.reshape((B, T, 1)).expand((B, T, min(self.r_u+self.r_d, min(u_len)))) + torch.arange(min(self.r_d+self.r_u, min(u_len)), device=encoder_out.device)
+
+ import fast_rnnt
+ am_pruned, lm_pruned = fast_rnnt.do_rnnt_pruning(
+ am=self.joint_network.lin_enc(encoder_out),
+ lm=self.joint_network.lin_dec(decoder_out),
+ ranges=ranges,
+ )
+
+ logits = self.joint_network(am_pruned, lm_pruned, project_input=False)
+
+ with torch.cuda.amp.autocast(enabled=False):
+ loss_trans = fast_rnnt.rnnt_loss_pruned(
+ logits=logits.float(),
+ symbols=target.long(),
+ ranges=ranges,
+ termination_symbol=self.blank_id,
+ boundary=boundary,
+ reduction="sum",
+ )
+
+ cer_trans, wer_trans = None, None
+ if not self.training and (self.report_cer or self.report_wer):
+ if self.error_calculator is None:
+ from funasr.modules.e2e_asr_common import ErrorCalculatorTransducer as ErrorCalculator
+ self.error_calculator = ErrorCalculator(
+ self.decoder,
+ self.joint_network,
+ self.token_list,
+ self.sym_space,
+ self.sym_blank,
+ report_cer=self.report_cer,
+ report_wer=self.report_wer,
+ )
+ cer_trans, wer_trans = self.error_calculator(encoder_out, target, t_len)
+
+ loss_ctc, loss_lm = 0.0, 0.0
+
+ if self.use_auxiliary_ctc:
+ loss_ctc = self._calc_ctc_loss(
+ encoder_out,
+ target,
+ t_len,
+ u_len,
+ )
+
+ if self.use_auxiliary_lm_loss:
+ loss_lm = self._calc_lm_loss(decoder_out, target)
+
+ loss = (
+ self.transducer_weight * loss_trans
+ + self.auxiliary_ctc_weight * loss_ctc
+ + self.auxiliary_lm_loss_weight * loss_lm
+ + self.predictor_weight * loss_pre
+ + self.cif_weight * loss_cif
+ )
+
+ stats = dict(
+ loss=loss.detach(),
+ loss_transducer=loss_trans.detach(),
+ loss_pre=loss_pre.detach(),
+ loss_cif=loss_cif.detach() if loss_cif > 0.0 else None,
+ aux_ctc_loss=loss_ctc.detach() if loss_ctc > 0.0 else None,
+ aux_lm_loss=loss_lm.detach() if loss_lm > 0.0 else None,
+ cer_transducer=cer_trans,
+ wer_transducer=wer_trans,
+ )
+
+ # force_gatherable: to-device and to-tensor if scalar for DataParallel
+ loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
+
+ return loss, stats, weight
+
+ def collect_feats(
+ self,
+ speech: torch.Tensor,
+ speech_lengths: torch.Tensor,
+ text: torch.Tensor,
+ text_lengths: torch.Tensor,
+ **kwargs,
+ ) -> Dict[str, torch.Tensor]:
+ """Collect features sequences and features lengths sequences.
+
+ Args:
+ speech: Speech sequences. (B, S)
+ speech_lengths: Speech sequences lengths. (B,)
+ text: Label ID sequences. (B, L)
+ text_lengths: Label ID sequences lengths. (B,)
+ kwargs: Contains "utts_id".
+
+ Return:
+ {}: "feats": Features sequences. (B, T, D_feats),
+ "feats_lengths": Features sequences lengths. (B,)
+
+ """
+ if self.extract_feats_in_collect_stats:
+ feats, feats_lengths = self._extract_feats(speech, speech_lengths)
+ else:
+ # Generate dummy stats if extract_feats_in_collect_stats is False
+ logging.warning(
+ "Generating dummy stats for feats and feats_lengths, "
+ "because encoder_conf.extract_feats_in_collect_stats is "
+ f"{self.extract_feats_in_collect_stats}"
+ )
+
+ feats, feats_lengths = speech, speech_lengths
+
+ return {"feats": feats, "feats_lengths": feats_lengths}
+
+ def encode(
+ self,
+ speech: torch.Tensor,
+ speech_lengths: torch.Tensor,
+ ) -> Tuple[torch.Tensor, torch.Tensor]:
+ """Encoder speech sequences.
+
+ Args:
+ speech: Speech sequences. (B, S)
+ speech_lengths: Speech sequences lengths. (B,)
+
+ Return:
+ encoder_out: Encoder outputs. (B, T, D_enc)
+ encoder_out_lens: Encoder outputs lengths. (B,)
+
+ """
+ with autocast(False):
+ # 1. Extract feats
+ feats, feats_lengths = self._extract_feats(speech, speech_lengths)
+
+ # 2. Data augmentation
+ if self.specaug is not None and self.training:
+ feats, feats_lengths = self.specaug(feats, feats_lengths)
+
+ # 3. Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
+ if self.normalize is not None:
+ feats, feats_lengths = self.normalize(feats, feats_lengths)
+
+ # 4. Forward encoder
+ encoder_out, encoder_out_lens, _ = self.encoder(feats, feats_lengths)
+
+ assert encoder_out.size(0) == speech.size(0), (
+ encoder_out.size(),
+ speech.size(0),
+ )
+ assert encoder_out.size(1) <= encoder_out_lens.max(), (
+ encoder_out.size(),
+ encoder_out_lens.max(),
+ )
+
+ return encoder_out, encoder_out_lens
+
+ def _extract_feats(
+ self, speech: torch.Tensor, speech_lengths: torch.Tensor
+ ) -> Tuple[torch.Tensor, torch.Tensor]:
+ """Extract features sequences and features sequences lengths.
+
+ Args:
+ speech: Speech sequences. (B, S)
+ speech_lengths: Speech sequences lengths. (B,)
+
+ Return:
+ feats: Features sequences. (B, T, D_feats)
+ feats_lengths: Features sequences lengths. (B,)
+
+ """
+ assert speech_lengths.dim() == 1, speech_lengths.shape
+
+ # for data-parallel
+ speech = speech[:, : speech_lengths.max()]
+
+ if self.frontend is not None:
+ feats, feats_lengths = self.frontend(speech, speech_lengths)
+ else:
+ feats, feats_lengths = speech, speech_lengths
+
+ return feats, feats_lengths
+
+ def _calc_ctc_loss(
+ self,
+ encoder_out: torch.Tensor,
+ target: torch.Tensor,
+ t_len: torch.Tensor,
+ u_len: torch.Tensor,
+ ) -> torch.Tensor:
+ """Compute CTC loss.
+
+ Args:
+ encoder_out: Encoder output sequences. (B, T, D_enc)
+ target: Target label ID sequences. (B, L)
+ t_len: Encoder output sequences lengths. (B,)
+ u_len: Target label ID sequences lengths. (B,)
+
+ Return:
+ loss_ctc: CTC loss value.
+
+ """
+ ctc_in = self.ctc_lin(
+ torch.nn.functional.dropout(encoder_out, p=self.ctc_dropout_rate)
+ )
+ ctc_in = torch.log_softmax(ctc_in.transpose(0, 1), dim=-1)
+
+ target_mask = target != 0
+ ctc_target = target[target_mask].cpu()
+
+ with torch.backends.cudnn.flags(deterministic=True):
+ loss_ctc = torch.nn.functional.ctc_loss(
+ ctc_in,
+ ctc_target,
+ t_len,
+ u_len,
+ zero_infinity=True,
+ reduction="sum",
+ )
+ loss_ctc /= target.size(0)
+
+ return loss_ctc
+
+ def _calc_lm_loss(
+ self,
+ decoder_out: torch.Tensor,
+ target: torch.Tensor,
+ ) -> torch.Tensor:
+ """Compute LM loss.
+
+ Args:
+ decoder_out: Decoder output sequences. (B, U, D_dec)
+ target: Target label ID sequences. (B, L)
+
+ Return:
+ loss_lm: LM loss value.
+
+ """
+ lm_loss_in = self.lm_lin(decoder_out[:, :-1, :]).view(-1, self.vocab_size)
+ lm_target = target.view(-1).type(torch.int64)
+
+ with torch.no_grad():
+ true_dist = lm_loss_in.clone()
+ true_dist.fill_(self.lm_loss_smoothing / (self.vocab_size - 1))
+
+ # Ignore blank ID (0)
+ ignore = lm_target == 0
+ lm_target = lm_target.masked_fill(ignore, 0)
+
+ true_dist.scatter_(1, lm_target.unsqueeze(1), (1 - self.lm_loss_smoothing))
+
+ loss_lm = torch.nn.functional.kl_div(
+ torch.log_softmax(lm_loss_in, dim=1),
+ true_dist,
+ reduction="none",
+ )
+ loss_lm = loss_lm.masked_fill(ignore.unsqueeze(1), 0).sum() / decoder_out.size(
+ 0
+ )
+
+ return loss_lm
diff --git a/funasr/models/e2e_asr_transducer.py b/funasr/models/e2e_asr_transducer.py
index 80914b1..729e918 100644
--- a/funasr/models/e2e_asr_transducer.py
+++ b/funasr/models/e2e_asr_transducer.py
@@ -353,11 +353,6 @@
"""
if self.criterion_transducer is None:
try:
- # from warprnnt_pytorch import RNNTLoss
- # self.criterion_transducer = RNNTLoss(
- # reduction="mean",
- # fastemit_lambda=self.fastemit_lambda,
- # )
from warp_rnnt import rnnt_loss as RNNTLoss
self.criterion_transducer = RNNTLoss
@@ -368,12 +363,6 @@
)
exit(1)
- # loss_transducer = self.criterion_transducer(
- # joint_out,
- # target,
- # t_len,
- # u_len,
- # )
log_probs = torch.log_softmax(joint_out, dim=-1)
loss_transducer = self.criterion_transducer(
@@ -637,7 +626,6 @@
batch_size = speech.shape[0]
text = text[:, : text_lengths.max()]
- #print(speech.shape)
# 1. Encoder
encoder_out, encoder_out_chunk, encoder_out_lens = self.encode(speech, speech_lengths)
@@ -854,11 +842,6 @@
"""
if self.criterion_transducer is None:
try:
- # from warprnnt_pytorch import RNNTLoss
- # self.criterion_transducer = RNNTLoss(
- # reduction="mean",
- # fastemit_lambda=self.fastemit_lambda,
- # )
from warp_rnnt import rnnt_loss as RNNTLoss
self.criterion_transducer = RNNTLoss
@@ -869,12 +852,6 @@
)
exit(1)
- # loss_transducer = self.criterion_transducer(
- # joint_out,
- # target,
- # t_len,
- # u_len,
- # )
log_probs = torch.log_softmax(joint_out, dim=-1)
loss_transducer = self.criterion_transducer(
diff --git a/funasr/models/predictor/cif.py b/funasr/models/predictor/cif.py
index 3c363db..c66af94 100644
--- a/funasr/models/predictor/cif.py
+++ b/funasr/models/predictor/cif.py
@@ -1,10 +1,12 @@
import torch
from torch import nn
+from torch import Tensor
import logging
import numpy as np
from funasr.torch_utils.device_funcs import to_device
from funasr.modules.nets_utils import make_pad_mask
from funasr.modules.streaming_utils.utils import sequence_mask
+from typing import Optional, Tuple
class CifPredictor(nn.Module):
def __init__(self, idim, l_order, r_order, threshold=1.0, dropout=0.1, smooth_factor=1.0, noise_threshold=0, tail_threshold=0.45):
@@ -747,3 +749,128 @@
predictor_alignments = index_div_bool_zeros_count_tile_out
predictor_alignments_length = predictor_alignments.sum(-1).type(encoder_sequence_length.dtype)
return predictor_alignments.detach(), predictor_alignments_length.detach()
+
+class BATPredictor(nn.Module):
+ def __init__(self, idim, l_order, r_order, threshold=1.0, dropout=0.1, smooth_factor=1.0, noise_threshold=0, return_accum=False):
+ super(BATPredictor, self).__init__()
+
+ self.pad = nn.ConstantPad1d((l_order, r_order), 0)
+ self.cif_conv1d = nn.Conv1d(idim, idim, l_order + r_order + 1, groups=idim)
+ self.cif_output = nn.Linear(idim, 1)
+ self.dropout = torch.nn.Dropout(p=dropout)
+ self.threshold = threshold
+ self.smooth_factor = smooth_factor
+ self.noise_threshold = noise_threshold
+ self.return_accum = return_accum
+
+ def cif(
+ self,
+ input: Tensor,
+ alpha: Tensor,
+ beta: float = 1.0,
+ return_accum: bool = False,
+ ) -> Tuple[Tensor, Tensor, Tensor, Tensor]:
+ B, S, C = input.size()
+ assert tuple(alpha.size()) == (B, S), f"{alpha.size()} != {(B, S)}"
+
+ dtype = alpha.dtype
+ alpha = alpha.float()
+
+ alpha_sum = alpha.sum(1)
+ feat_lengths = (alpha_sum / beta).floor().long()
+ T = feat_lengths.max()
+
+ # aggregate and integrate
+ csum = alpha.cumsum(-1)
+ with torch.no_grad():
+ # indices used for scattering
+ right_idx = (csum / beta).floor().long().clip(max=T)
+ left_idx = right_idx.roll(1, dims=1)
+ left_idx[:, 0] = 0
+
+ # count # of fires from each source
+ fire_num = right_idx - left_idx
+ extra_weights = (fire_num - 1).clip(min=0)
+ # The extra entry in last dim is for
+ output = input.new_zeros((B, T + 1, C))
+ source_range = torch.arange(1, 1 + S).unsqueeze(0).type_as(input)
+ zero = alpha.new_zeros((1,))
+
+ # right scatter
+ fire_mask = fire_num > 0
+ right_weight = torch.where(
+ fire_mask,
+ csum - right_idx.type_as(alpha) * beta,
+ zero
+ ).type_as(input)
+ # assert right_weight.ge(0).all(), f"{right_weight} should be non-negative."
+ output.scatter_add_(
+ 1,
+ right_idx.unsqueeze(-1).expand(-1, -1, C),
+ right_weight.unsqueeze(-1) * input
+ )
+
+ # left scatter
+ left_weight = (
+ alpha - right_weight - extra_weights.type_as(alpha) * beta
+ ).type_as(input)
+ output.scatter_add_(
+ 1,
+ left_idx.unsqueeze(-1).expand(-1, -1, C),
+ left_weight.unsqueeze(-1) * input
+ )
+
+ # extra scatters
+ if extra_weights.ge(0).any():
+ extra_steps = extra_weights.max().item()
+ tgt_idx = left_idx
+ src_feats = input * beta
+ for _ in range(extra_steps):
+ tgt_idx = (tgt_idx + 1).clip(max=T)
+ # (B, S, 1)
+ src_mask = (extra_weights > 0)
+ output.scatter_add_(
+ 1,
+ tgt_idx.unsqueeze(-1).expand(-1, -1, C),
+ src_feats * src_mask.unsqueeze(2)
+ )
+ extra_weights -= 1
+
+ output = output[:, :T, :]
+
+ if return_accum:
+ return output, csum
+ else:
+ return output, alpha
+
+ def forward(self, hidden, target_label=None, mask=None, ignore_id=-1, mask_chunk_predictor=None, target_label_length=None):
+ h = hidden
+ context = h.transpose(1, 2)
+ queries = self.pad(context)
+ memory = self.cif_conv1d(queries)
+ output = memory + context
+ output = self.dropout(output)
+ output = output.transpose(1, 2)
+ output = torch.relu(output)
+ output = self.cif_output(output)
+ alphas = torch.sigmoid(output)
+ alphas = torch.nn.functional.relu(alphas*self.smooth_factor - self.noise_threshold)
+ if mask is not None:
+ alphas = alphas * mask.transpose(-1, -2).float()
+ if mask_chunk_predictor is not None:
+ alphas = alphas * mask_chunk_predictor
+ alphas = alphas.squeeze(-1)
+ if target_label_length is not None:
+ target_length = target_label_length
+ elif target_label is not None:
+ target_length = (target_label != ignore_id).float().sum(-1)
+ # logging.info("target_length: {}".format(target_length))
+ else:
+ target_length = None
+ token_num = alphas.sum(-1)
+ if target_length is not None:
+ # length_noise = torch.rand(alphas.size(0), device=alphas.device) - 0.5
+ # target_length = length_noise + target_length
+ alphas *= ((target_length + 1e-4) / token_num)[:, None].repeat(1, alphas.size(1))
+ acoustic_embeds, cif_peak = self.cif(hidden, alphas, self.threshold, self.return_accum)
+ return acoustic_embeds, token_num, alphas, cif_peak
diff --git a/funasr/modules/embedding.py b/funasr/modules/embedding.py
index aaac80a..374eba4 100644
--- a/funasr/modules/embedding.py
+++ b/funasr/modules/embedding.py
@@ -393,8 +393,9 @@
def encode(self, positions: torch.Tensor = None, depth: int = None, dtype: torch.dtype = torch.float32):
batch_size = positions.size(0)
positions = positions.type(dtype)
- log_timescale_increment = torch.log(torch.tensor([10000], dtype=dtype)) / (depth / 2 - 1)
- inv_timescales = torch.exp(torch.arange(depth / 2).type(dtype) * (-log_timescale_increment))
+ device = positions.device
+ log_timescale_increment = torch.log(torch.tensor([10000], dtype=dtype, device=device)) / (depth / 2 - 1)
+ inv_timescales = torch.exp(torch.arange(depth / 2, device=device).type(dtype) * (-log_timescale_increment))
inv_timescales = torch.reshape(inv_timescales, [batch_size, -1])
scaled_time = torch.reshape(positions, [1, -1, 1]) * torch.reshape(inv_timescales, [1, 1, -1])
encoding = torch.cat([torch.sin(scaled_time), torch.cos(scaled_time)], dim=2)
@@ -402,7 +403,7 @@
def forward(self, x):
batch_size, timesteps, input_dim = x.size()
- positions = torch.arange(1, timesteps+1)[None, :]
+ positions = torch.arange(1, timesteps+1, device=x.device)[None, :]
position_encoding = self.encode(positions, input_dim, x.dtype).to(x.device)
return x + position_encoding
diff --git a/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh b/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh
new file mode 100644
index 0000000..97e327c
--- /dev/null
+++ b/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh
@@ -0,0 +1,1450 @@
+#!/usr/bin/env bash
+
+scriptVersion="0.0.4"
+scriptDate="20230702"
+
+
+# Set color
+RED="\033[31;1m"
+GREEN="\033[32;1m"
+YELLOW="\033[33;1m"
+BLUE="\033[34;1m"
+CYAN="\033[36;1m"
+PLAIN="\033[0m"
+
+# Info messages
+DONE="${GREEN}[DONE]${PLAIN}"
+ERROR="${RED}[ERROR]${PLAIN}"
+WARNING="${YELLOW}[WARNING]${PLAIN}"
+
+# Font Format
+BOLD="\033[1m"
+UNDERLINE="\033[4m"
+
+# Current folder
+cur_dir=`pwd`
+
+
+DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS="https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/funasr/runtime/docs/docker_offline_cpu_zh_lists"
+DEFAULT_DOCKER_IMAGE_LISTS=$DEFAULT_DOCKER_OFFLINE_CPU_ZH_LISTS
+DEFAULT_FUNASR_DOCKER_URL="registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr"
+DEFAULT_FUNASR_RUNTIME_RESOURCES="funasr-runtime-resources"
+DEFAULT_FUNASR_LOCAL_WORKSPACE="${cur_dir}/${DEFAULT_FUNASR_RUNTIME_RESOURCES}"
+DEFAULT_FUNASR_CONFIG_DIR="/var/funasr"
+DEFAULT_FUNASR_CONFIG_FILE="${DEFAULT_FUNASR_CONFIG_DIR}/config"
+DEFAULT_FUNASR_PROGRESS_TXT="${DEFAULT_FUNASR_CONFIG_DIR}/progress.txt"
+DEFAULT_FUNASR_SERVER_LOG="${DEFAULT_FUNASR_CONFIG_DIR}/server_console.log"
+DEFAULT_FUNASR_WORKSPACE_DIR="/workspace/models"
+DEFAULT_DOCKER_PORT="10095"
+DEFAULT_PROGRESS_FILENAME="progress.txt"
+DEFAULT_SERVER_EXEC_NAME="funasr-wss-server"
+DEFAULT_DOCKER_EXEC_DIR="/workspace/FunASR/funasr/runtime/websocket/build/bin"
+DEFAULT_DOCKER_EXEC_PATH=${DEFAULT_DOCKER_EXEC_DIR}/${DEFAULT_SERVER_EXEC_NAME}
+DEFAULT_SAMPLES_NAME="funasr_samples"
+DEFAULT_SAMPLES_DIR="samples"
+DEFAULT_SAMPLES_URL="https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/${DEFAULT_SAMPLES_NAME}.tar.gz"
+
+SAMPLE_CLIENTS=( \
+"Python" \
+"Linux_Cpp" \
+)
+DOCKER_IMAGES=()
+
+# Handles the download progress bar
+asr_percent_int=0
+vad_percent_int=0
+punc_percent_int=0
+asr_title="Downloading"
+asr_percent="0"
+asr_speed="0KB/s"
+asr_revision=""
+vad_title="Downloading"
+vad_percent="0"
+vad_speed="0KB/s"
+vad_revision=""
+punc_title="Downloading"
+punc_percent="0"
+punc_speed="0KB/s"
+punc_revision=""
+serverProgress(){
+ status_flag="STATUS:"
+ stage=0
+ wait=0
+ server_status=""
+
+ while true
+ do
+ if [ -f "$DEFAULT_FUNASR_PROGRESS_TXT" ]; then
+ break
+ else
+ sleep 1
+ let wait=wait+1
+ if [ ${wait} -ge 6 ]; then
+ break
+ fi
+ fi
+ done
+
+ if [ ! -f "$DEFAULT_FUNASR_PROGRESS_TXT" ]; then
+ echo -e " ${RED}The note of progress does not exist.($DEFAULT_FUNASR_PROGRESS_TXT) ${PLAIN}"
+ return 98
+ fi
+
+ stage=1
+ while read line
+ do
+ if [ $stage -eq 1 ]; then
+ result=$(echo $line | grep "STATUS:")
+ if [ "$result" != "" ]; then
+ stage=2
+ server_status=${line#*:}
+ status=`expr $server_status + 0`
+ if [ $status -eq 99 ]; then
+ stage=99
+ fi
+ continue
+ fi
+ elif [ $stage -eq 2 ]; then
+ result=$(echo $line | grep "ASR")
+ if [ "$result" != "" ]; then
+ stage=3
+ continue
+ fi
+ elif [ $stage -eq 3 ]; then
+ result=$(echo $line | grep "VAD")
+ if [ "$result" != "" ]; then
+ stage=4
+ continue
+ fi
+ result=$(echo $line | grep "title:")
+ if [ "$result" != "" ]; then
+ asr_title=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "percent:")
+ if [ "$result" != "" ]; then
+ asr_percent=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "speed:")
+ if [ "$result" != "" ]; then
+ asr_speed=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "revision:")
+ if [ "$result" != "" ]; then
+ asr_revision=${line#*:}
+ continue
+ fi
+ elif [ $stage -eq 4 ]; then
+ result=$(echo $line | grep "PUNC")
+ if [ "$result" != "" ]; then
+ stage=5
+ continue
+ fi
+ result=$(echo $line | grep "title:")
+ if [ "$result" != "" ]; then
+ vad_title=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "percent:")
+ if [ "$result" != "" ]; then
+ vad_percent=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "speed:")
+ if [ "$result" != "" ]; then
+ vad_speed=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "revision:")
+ if [ "$result" != "" ]; then
+ vad_revision=${line#*:}
+ continue
+ fi
+ elif [ $stage -eq 5 ]; then
+ result=$(echo $line | grep "DONE")
+ if [ "$result" != "" ]; then
+ # Done and break.
+ stage=6
+ break
+ fi
+ result=$(echo $line | grep "title:")
+ if [ "$result" != "" ]; then
+ punc_title=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "percent:")
+ if [ "$result" != "" ]; then
+ punc_percent=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "speed:")
+ if [ "$result" != "" ]; then
+ punc_speed=${line#*:}
+ continue
+ fi
+ result=$(echo $line | grep "revision:")
+ if [ "$result" != "" ]; then
+ punc_revision=${line#*:}
+ continue
+ fi
+ elif [ $stage -eq 99 ]; then
+ echo -e " ${RED}ERROR: $line${PLAIN}"
+ fi
+ done < $DEFAULT_FUNASR_PROGRESS_TXT
+
+ if [ $stage -ne 99 ]; then
+ drawProgress "ASR " $asr_title $asr_percent $asr_speed $asr_revision $asr_percent_int
+ asr_percent_int=$?
+ drawProgress "VAD " $vad_title $vad_percent $vad_speed $vad_revision $vad_percent_int
+ vad_percent_int=$?
+ drawProgress "PUNC" $punc_title $punc_percent $punc_speed $punc_revision $punc_percent_int
+ punc_percent_int=$?
+ fi
+
+ return $stage
+}
+
+drawProgress(){
+ model=$1
+ title=$2
+ percent_str=$3
+ speed=$4
+ revision=$5
+ latest_percent=$6
+
+ progress=0
+ if [ ! -z "$percent_str" ]; then
+ progress=`expr $percent_str + 0`
+ latest_percent=`expr $latest_percent + 0`
+ if [ $progress -ne 0 ] && [ $progress -lt $latest_percent ]; then
+ progress=$latest_percent
+ fi
+ fi
+
+ loading_flag="Loading"
+ if [ "$title" = "$loading_flag" ]; then
+ progress=100
+ fi
+
+ i=0
+ str=""
+ let max=progress/2
+ while [ $i -lt $max ]
+ do
+ let i++
+ str+='='
+ done
+ let color=36
+ let index=max*2
+ if [ -z "$speed" ]; then
+ printf "\r \e[0;${CYAN}[%s][%-11s][%-50s][%d%%][%s]\e[0m" "$model" "$title" "$str" "$$index" "$revision"
+ else
+ printf "\r \e[0;${CYAN}[%s][%-11s][%-50s][%3d%%][%8s][%s]\e[0m" "$model" "$title" "$str" "$index" "$speed" "$revision"
+ fi
+ printf "\n"
+
+ return $progress
+}
+
+menuSelection(){
+ local menu
+ menu=($(echo "$@"))
+ result=1
+ show_no=1
+ menu_no=0
+ len=${#menu[@]}
+
+ while true
+ do
+ echo -e " ${BOLD}${show_no})${PLAIN} ${menu[menu_no]}"
+
+ let show_no++
+ let menu_no++
+ if [ $menu_no -ge $len ]; then
+ break
+ fi
+ done
+
+ while true
+ do
+ echo -e " Enter your choice, default(${CYAN}1${PLAIN}): \c"
+ read result
+ if [ -z "$result" ]; then
+ result=1
+ fi
+
+ expr $result + 0 &>/dev/null
+ if [ $? -eq 0 ]; then
+ if [ $result -ge 1 ] && [ $result -le $len ]; then
+ break
+ else
+ echo -e " ${RED}Input error, please input correct number!${PLAIN}"
+ fi
+ else
+ echo -e " ${RED}Input error, please input correct number!${PLAIN}"
+ fi
+ done
+
+ return $result
+}
+
+
+full_path=""
+relativePathToFullPath(){
+ relativePath=$1
+ firstChar=${relativePath: 0: 1}
+ if [[ "$firstChar" == "" ]]; then
+ full_path=$relativePath
+ elif [[ "$firstChar" == "/" ]]; then
+ full_path=$relativePath
+ fi
+
+ tmpPath1=`dirname $relativePath`
+ tmpFullpath1=`cd $tmpPath1 && pwd`
+ tmpPath2=`basename $relativePath`
+ full_path=${tmpFullpath1}/${tmpPath2}
+}
+
+initConfiguration(){
+ if [ ! -z "$DEFAULT_FUNASR_CONFIG_DIR" ]; then
+ mkdir -p $DEFAULT_FUNASR_CONFIG_DIR
+ fi
+ if [ ! -f $DEFAULT_FUNASR_CONFIG_FILE ]; then
+ touch $DEFAULT_FUNASR_CONFIG_FILE
+ fi
+}
+
+initParameters(){
+ # Init workspace in local by new parameters.
+ PARAMS_FUNASR_SAMPLES_LOCAL_PATH=${PARAMS_FUNASR_LOCAL_WORKSPACE}/${DEFAULT_SAMPLES_NAME}.tar.gz
+ PARAMS_FUNASR_SAMPLES_LOCAL_DIR=${PARAMS_FUNASR_LOCAL_WORKSPACE}/${DEFAULT_SAMPLES_DIR}
+ PARAMS_FUNASR_LOCAL_MODELS_DIR="${PARAMS_FUNASR_LOCAL_WORKSPACE}/models"
+
+ if [ ! -z "$PARAMS_FUNASR_LOCAL_WORKSPACE" ]; then
+ mkdir -p $PARAMS_FUNASR_LOCAL_WORKSPACE
+ fi
+ if [ ! -z "$PARAMS_FUNASR_LOCAL_MODELS_DIR" ]; then
+ mkdir -p $PARAMS_FUNASR_LOCAL_MODELS_DIR
+ fi
+}
+
+# Parse the parameters from the docker list file.
+docker_info_cur_key=""
+docker_info_cur_val=""
+findTypeOfDockerInfo(){
+ line=$1
+ result=$(echo $line | grep ":")
+ if [ "$result" != "" ]; then
+ docker_info_cur_key=$result
+ docker_info_cur_val=""
+ else
+ docker_info_cur_val=$(echo $line)
+ fi
+}
+
+# Get a list of docker images.
+readDockerInfoFromUrl(){
+ list_url=$DEFAULT_DOCKER_IMAGE_LISTS
+ while true
+ do
+ content=$(curl --connect-timeout 10 -m 10 -s $list_url)
+ if [ ! -z "$content" ]; then
+ break
+ else
+ echo -e " ${RED}Unable to get docker image list due to network issues, try again.${PLAIN}"
+ fi
+ done
+ array=($(echo "$content"))
+ len=${#array[@]}
+
+ stage=0
+ docker_flag="DOCKER:"
+ judge_flag=":"
+ for i in ${array[@]}
+ do
+ findTypeOfDockerInfo $i
+ if [ "$docker_info_cur_key" = "DOCKER:" ]; then
+ if [ ! -z "$docker_info_cur_val" ]; then
+ docker_name=${DEFAULT_FUNASR_DOCKER_URL}:${docker_info_cur_val}
+ DOCKER_IMAGES[${#DOCKER_IMAGES[*]}]=$docker_name
+ fi
+ elif [ "$docker_info_cur_key" = "DEFAULT_ASR_MODEL:" ]; then
+ if [ ! -z "$docker_info_cur_val" ]; then
+ PARAMS_ASR_ID=$docker_info_cur_val
+ fi
+ elif [ "$docker_info_cur_key" = "DEFAULT_VAD_MODEL:" ]; then
+ if [ ! -z "$docker_info_cur_val" ]; then
+ PARAMS_VAD_ID=$docker_info_cur_val
+ fi
+ elif [ "$docker_info_cur_key" = "DEFAULT_PUNC_MODEL:" ]; then
+ if [ ! -z "$docker_info_cur_val" ]; then
+ PARAMS_PUNC_ID=$docker_info_cur_val
+ fi
+ fi
+ done
+ echo -e " $DONE"
+}
+
+# Make sure root user.
+rootNess(){
+ echo -e "${UNDERLINE}${BOLD}[0/5]${PLAIN}"
+ echo -e " ${YELLOW}Please check root access.${PLAIN}"
+
+ echo -e " ${WARNING} MUST RUN AS ${RED}ROOT${PLAIN} USER!"
+ if [[ $EUID -ne 0 ]]; then
+ echo -e " ${ERROR} MUST RUN AS ${RED}ROOT${PLAIN} USER!"
+ fi
+
+ cd $cur_dir
+ echo
+}
+
+# Get a list of docker images and select them.
+selectDockerImages(){
+ echo -e "${UNDERLINE}${BOLD}[1/5]${PLAIN}"
+ echo -e " ${YELLOW}Getting the list of docker images, please wait a few seconds.${PLAIN}"
+ readDockerInfoFromUrl
+ echo
+
+ echo -e " ${YELLOW}Please choose the Docker image.${PLAIN}"
+ menuSelection ${DOCKER_IMAGES[*]}
+ result=$?
+ index=`expr $result - 1`
+
+ PARAMS_DOCKER_IMAGE=${DOCKER_IMAGES[${index}]}
+ echo -e " ${UNDERLINE}You have chosen the Docker image:${PLAIN} ${GREEN}${PARAMS_DOCKER_IMAGE}${PLAIN}"
+
+ checkDockerExist
+ result=$?
+ result=`expr $result + 0`
+ if [ ${result} -eq 50 ]; then
+ return 50
+ fi
+
+ echo
+}
+
+# Configure FunASR server host port setting.
+setupHostPort(){
+ echo -e "${UNDERLINE}${BOLD}[2/5]${PLAIN}"
+
+ params_host_port=`sed '/^PARAMS_HOST_PORT=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ -z "$params_host_port" ]; then
+ PARAMS_HOST_PORT="10095"
+ else
+ PARAMS_HOST_PORT=$params_host_port
+ fi
+
+ while true
+ do
+ echo -e " ${YELLOW}Please input the opened port in the host used for FunASR server.${PLAIN}"
+ echo -e " Setting the opened host port [1-65535], default(${CYAN}${PARAMS_HOST_PORT}${PLAIN}): \c"
+ read PARAMS_HOST_PORT
+
+ if [ -z "$PARAMS_HOST_PORT" ]; then
+ params_host_port=`sed '/^PARAMS_HOST_PORT=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ -z "$params_host_port" ]; then
+ PARAMS_HOST_PORT="10095"
+ else
+ PARAMS_HOST_PORT=$params_host_port
+ fi
+ fi
+ expr $PARAMS_HOST_PORT + 0 &>/dev/null
+ if [ $? -eq 0 ]; then
+ if [ $PARAMS_HOST_PORT -ge 1 ] && [ $PARAMS_HOST_PORT -le 65535 ]; then
+ echo -e " ${UNDERLINE}The port of the host is${PLAIN} ${GREEN}${PARAMS_HOST_PORT}${PLAIN}"
+ echo -e " ${UNDERLINE}The port in Docker for FunASR server is${PLAIN} ${GREEN}${PARAMS_DOCKER_PORT}${PLAIN}"
+ break
+ else
+ echo -e " ${RED}Input error, please input correct number!${PLAIN}"
+ fi
+ else
+ echo -e " ${RED}Input error, please input correct number!${PLAIN}"
+ fi
+ done
+ echo
+}
+
+complementParameters(){
+ # parameters about ASR model
+ if [ ! -z "$PARAMS_ASR_ID" ]; then
+ PARAMS_DOCKER_ASR_PATH=${PARAMS_DOWNLOAD_MODEL_DIR}/${PARAMS_ASR_ID}
+ PARAMS_DOCKER_ASR_DIR=$(dirname "$PARAMS_DOCKER_ASR_PATH")
+ PARAMS_LOCAL_ASR_PATH=${PARAMS_FUNASR_LOCAL_MODELS_DIR}/${PARAMS_ASR_ID}
+ PARAMS_LOCAL_ASR_DIR=$(dirname "$PARAMS_LOCAL_ASR_PATH")
+ fi
+
+ # parameters about VAD model
+ if [ ! -z "$PARAMS_VAD_ID" ]; then
+ PARAMS_DOCKER_VAD_PATH=${PARAMS_DOWNLOAD_MODEL_DIR}/${PARAMS_VAD_ID}
+ PARAMS_DOCKER_VAD_DIR=$(dirname "$PARAMS_DOCKER_VAD_PATH")
+ PARAMS_LOCAL_VAD_PATH=${PARAMS_FUNASR_LOCAL_MODELS_DIR}/${PARAMS_VAD_ID}
+ PARAMS_LOCAL_VAD_DIR=$(dirname "$PARAMS_LOCAL_VAD_PATH")
+ fi
+
+ # parameters about PUNC model
+ if [ ! -z "$PARAMS_PUNC_ID" ]; then
+ PARAMS_DOCKER_PUNC_PATH=${PARAMS_DOWNLOAD_MODEL_DIR}/${PARAMS_PUNC_ID}
+ PARAMS_DOCKER_PUNC_DIR=$(dirname "${PARAMS_DOCKER_PUNC_PATH}")
+ PARAMS_LOCAL_PUNC_PATH=${PARAMS_FUNASR_LOCAL_MODELS_DIR}/${PARAMS_PUNC_ID}
+ PARAMS_LOCAL_PUNC_DIR=$(dirname "${PARAMS_LOCAL_PUNC_PATH}")
+ fi
+
+ # parameters about thread_num
+ params_decoder_thread_num=`sed '/^PARAMS_DECODER_THREAD_NUM=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ -z "$params_decoder_thread_num" ]; then
+ PARAMS_DECODER_THREAD_NUM=$CPUNUM
+ else
+ PARAMS_DECODER_THREAD_NUM=$params_decoder_thread_num
+ fi
+
+ multiple_io=4
+ PARAMS_DECODER_THREAD_NUM=`expr ${PARAMS_DECODER_THREAD_NUM} + 0`
+ PARAMS_IO_THREAD_NUM=`expr ${PARAMS_DECODER_THREAD_NUM} / ${multiple_io}`
+ if [ $PARAMS_IO_THREAD_NUM -eq 0 ]; then
+ PARAMS_IO_THREAD_NUM=1
+ fi
+}
+
+paramsFromDefault(){
+ initConfiguration
+
+ echo -e " ${YELLOW}Load parameters from${PLAIN} ${GREEN}${DEFAULT_FUNASR_CONFIG_FILE}${PLAIN}"
+ echo
+
+ funasr_local_workspace=`sed '/^PARAMS_FUNASR_LOCAL_WORKSPACE=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$funasr_local_workspace" ]; then
+ PARAMS_FUNASR_LOCAL_WORKSPACE=$funasr_local_workspace
+ fi
+ funasr_samples_local_dir=`sed '/^PARAMS_FUNASR_SAMPLES_LOCAL_DIR=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$funasr_samples_local_dir" ]; then
+ PARAMS_FUNASR_SAMPLES_LOCAL_DIR=$funasr_samples_local_dir
+ fi
+ funasr_samples_local_path=`sed '/^PARAMS_FUNASR_SAMPLES_LOCAL_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$funasr_samples_local_path" ]; then
+ PARAMS_FUNASR_SAMPLES_LOCAL_PATH=$funasr_samples_local_path
+ fi
+ funasr_local_models_dir=`sed '/^PARAMS_FUNASR_LOCAL_MODELS_DIR=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$funasr_local_models_dir" ]; then
+ PARAMS_FUNASR_LOCAL_MODELS_DIR=$funasr_local_models_dir
+ fi
+ funasr_config_path=`sed '/^PARAMS_FUNASR_CONFIG_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$funasr_config_path" ]; then
+ PARAMS_FUNASR_CONFIG_PATH=$funasr_config_path
+ fi
+
+ docker_image=`sed '/^PARAMS_DOCKER_IMAGE=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_image" ]; then
+ PARAMS_DOCKER_IMAGE=$docker_image
+ fi
+ download_model_dir=`sed '/^PARAMS_DOWNLOAD_MODEL_DIR=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$download_model_dir" ]; then
+ PARAMS_DOWNLOAD_MODEL_DIR=$download_model_dir
+ fi
+ PARAMS_LOCAL_ASR_PATH=`sed '/^PARAMS_LOCAL_ASR_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$local_asr_path" ]; then
+ PARAMS_LOCAL_ASR_PATH=$local_asr_path
+ fi
+ docker_asr_path=`sed '/^PARAMS_DOCKER_ASR_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_asr_path" ]; then
+ PARAMS_DOCKER_ASR_PATH=$docker_asr_path
+ fi
+ asr_id=`sed '/^PARAMS_ASR_ID=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$asr_id" ]; then
+ PARAMS_ASR_ID=$asr_id
+ fi
+ local_vad_path=`sed '/^PARAMS_LOCAL_VAD_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$local_vad_path" ]; then
+ PARAMS_LOCAL_VAD_PATH=$local_vad_path
+ fi
+ docker_vad_path=`sed '/^PARAMS_DOCKER_VAD_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_vad_path" ]; then
+ PARAMS_DOCKER_VAD_PATH=$docker_vad_path
+ fi
+ vad_id=`sed '/^PARAMS_VAD_ID=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$vad_id" ]; then
+ PARAMS_VAD_ID=$vad_id
+ fi
+ local_punc_path=`sed '/^PARAMS_LOCAL_PUNC_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$local_punc_path" ]; then
+ PARAMS_LOCAL_PUNC_PATH=$local_punc_path
+ fi
+ docker_punc_path=`sed '/^PARAMS_DOCKER_PUNC_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_punc_path" ]; then
+ PARAMS_DOCKER_PUNC_PATH=$docker_punc_path
+ fi
+ punc_id=`sed '/^PARAMS_PUNC_ID=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$punc_id" ]; then
+ PARAMS_PUNC_ID=$punc_id
+ fi
+ docker_exec_path=`sed '/^PARAMS_DOCKER_EXEC_PATH=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_exec_path" ]; then
+ PARAMS_DOCKER_EXEC_PATH=$docker_exec_path
+ fi
+ host_port=`sed '/^PARAMS_HOST_PORT=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$host_port" ]; then
+ PARAMS_HOST_PORT=$host_port
+ fi
+ docker_port=`sed '/^PARAMS_DOCKER_PORT=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$docker_port" ]; then
+ PARAMS_DOCKER_PORT=$docker_port
+ fi
+ decode_thread_num=`sed '/^PARAMS_DECODER_THREAD_NUM=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$decode_thread_num" ]; then
+ PARAMS_DECODER_THREAD_NUM=$decode_thread_num
+ fi
+ io_thread_num=`sed '/^PARAMS_IO_THREAD_NUM=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ ! -z "$io_thread_num" ]; then
+ PARAMS_IO_THREAD_NUM=$io_thread_num
+ fi
+}
+
+saveParams(){
+ echo "$i" > $DEFAULT_FUNASR_CONFIG_FILE
+ echo -e " ${GREEN}Parameters are stored in the file ${DEFAULT_FUNASR_CONFIG_FILE}${PLAIN}"
+
+ echo "PARAMS_DOCKER_IMAGE=${PARAMS_DOCKER_IMAGE}" > $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_FUNASR_LOCAL_WORKSPACE=${PARAMS_FUNASR_LOCAL_WORKSPACE}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_FUNASR_SAMPLES_LOCAL_DIR=${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_FUNASR_SAMPLES_LOCAL_PATH=${PARAMS_FUNASR_SAMPLES_LOCAL_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_FUNASR_LOCAL_MODELS_DIR=${PARAMS_FUNASR_LOCAL_MODELS_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_FUNASR_CONFIG_PATH=${PARAMS_FUNASR_CONFIG_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_DOWNLOAD_MODEL_DIR=${PARAMS_DOWNLOAD_MODEL_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_DOCKER_EXEC_PATH=${PARAMS_DOCKER_EXEC_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_EXEC_DIR=${PARAMS_DOCKER_EXEC_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_LOCAL_ASR_PATH=${PARAMS_LOCAL_ASR_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_LOCAL_ASR_DIR=${PARAMS_LOCAL_ASR_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_ASR_PATH=${PARAMS_DOCKER_ASR_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_ASR_DIR=${PARAMS_DOCKER_ASR_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_ASR_ID=${PARAMS_ASR_ID}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_LOCAL_PUNC_PATH=${PARAMS_LOCAL_PUNC_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_LOCAL_PUNC_DIR=${PARAMS_LOCAL_PUNC_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_PUNC_PATH=${PARAMS_DOCKER_PUNC_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_PUNC_DIR=${PARAMS_DOCKER_PUNC_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_PUNC_ID=${PARAMS_PUNC_ID}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_LOCAL_VAD_PATH=${PARAMS_LOCAL_VAD_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_LOCAL_VAD_DIR=${PARAMS_LOCAL_VAD_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_VAD_PATH=${PARAMS_DOCKER_VAD_PATH}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_VAD_DIR=${PARAMS_DOCKER_VAD_DIR}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_VAD_ID=${PARAMS_VAD_ID}" >> $DEFAULT_FUNASR_CONFIG_FILE
+
+ echo "PARAMS_HOST_PORT=${PARAMS_HOST_PORT}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DOCKER_PORT=${PARAMS_DOCKER_PORT}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_DECODER_THREAD_NUM=${PARAMS_DECODER_THREAD_NUM}" >> $DEFAULT_FUNASR_CONFIG_FILE
+ echo "PARAMS_IO_THREAD_NUM=${PARAMS_IO_THREAD_NUM}" >> $DEFAULT_FUNASR_CONFIG_FILE
+}
+
+showAllParams(){
+ echo -e "${UNDERLINE}${BOLD}[3/5]${PLAIN}"
+ echo -e " ${YELLOW}Show parameters of FunASR server setting and confirm to run ...${PLAIN}"
+ echo
+
+ if [ ! -z "$PARAMS_DOCKER_IMAGE" ]; then
+ echo -e " The current Docker image is : ${GREEN}${PARAMS_DOCKER_IMAGE}${PLAIN}"
+ fi
+ if [ ! -z "$PARAMS_FUNASR_LOCAL_WORKSPACE" ]; then
+ echo -e " The local workspace path is : ${GREEN}${PARAMS_FUNASR_LOCAL_WORKSPACE}${PLAIN}"
+ fi
+
+ if [ ! -z "$PARAMS_DOWNLOAD_MODEL_DIR" ]; then
+ echo -e " The model will be automatically downloaded in Docker : ${GREEN}${PARAMS_DOWNLOAD_MODEL_DIR}${PLAIN}"
+ fi
+ echo
+
+ if [ ! -z "$PARAMS_ASR_ID" ]; then
+ echo -e " The ASR model_id used : ${GREEN}${PARAMS_ASR_ID}${PLAIN}"
+ fi
+ if [ ! -z "$PARAMS_LOCAL_ASR_PATH" ]; then
+ echo -e " The path to the local ASR model directory for the load : ${GREEN}${PARAMS_LOCAL_ASR_PATH}${PLAIN}"
+ fi
+ echo -e " The ASR model directory corresponds to the directory in Docker : ${GREEN}${PARAMS_DOCKER_ASR_PATH}${PLAIN}"
+
+ if [ ! -z "$PARAMS_VAD_ID" ]; then
+ echo -e " The VAD model_id used : ${GREEN}${PARAMS_VAD_ID}${PLAIN}"
+ fi
+ if [ ! -z "$PARAMS_LOCAL_VAD_PATH" ]; then
+ echo -e " The path to the local VAD model directory for the load : ${GREEN}${PARAMS_LOCAL_VAD_PATH}${PLAIN}"
+ fi
+ echo -e " The VAD model directory corresponds to the directory in Docker : ${GREEN}${PARAMS_DOCKER_VAD_PATH}${PLAIN}"
+
+ if [ ! -z "$PARAMS_PUNC_ID" ]; then
+ echo -e " The PUNC model_id used : ${GREEN}${PARAMS_PUNC_ID}${PLAIN}"
+ fi
+ if [ ! -z "$PARAMS_LOCAL_PUNC_PATH" ]; then
+ echo -e " The path to the local PUNC model directory for the load : ${GREEN}${PARAMS_LOCAL_PUNC_PATH}${PLAIN}"
+ fi
+ echo -e " The PUNC model directory corresponds to the directory in Docker: ${GREEN}${PARAMS_DOCKER_PUNC_PATH}${PLAIN}"
+ echo
+
+ echo -e " The path in the docker of the FunASR service executor : ${GREEN}${PARAMS_DOCKER_EXEC_PATH}${PLAIN}"
+
+ echo -e " Set the host port used for use by the FunASR service : ${GREEN}${PARAMS_HOST_PORT}${PLAIN}"
+ echo -e " Set the docker port used by the FunASR service : ${GREEN}${PARAMS_DOCKER_PORT}${PLAIN}"
+
+ echo -e " Set the number of threads used for decoding the FunASR service : ${GREEN}${PARAMS_DECODER_THREAD_NUM}${PLAIN}"
+ echo -e " Set the number of threads used for IO the FunASR service : ${GREEN}${PARAMS_IO_THREAD_NUM}${PLAIN}"
+ echo
+
+ if [ ! -z "$PARAMS_FUNASR_SAMPLES_LOCAL_DIR" ]; then
+ echo -e " Sample code will be store in local : ${GREEN}${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}${PLAIN}"
+ fi
+
+ echo
+ while true
+ do
+ params_confirm="y"
+ echo -e " ${YELLOW}Please input [Y/n] to confirm the parameters.${PLAIN}"
+ echo -e " [y] Verify that these parameters are correct and that the service will run."
+ echo -e " [n] The parameters set are incorrect, it will be rolled out, please rerun."
+ echo -e " read confirmation[${CYAN}Y${PLAIN}/n]: \c"
+ read params_confirm
+
+ if [ -z "$params_confirm" ]; then
+ params_confirm="y"
+ fi
+ YES="Y"
+ yes="y"
+ NO="N"
+ no="n"
+ echo
+ if [ "$params_confirm" = "$YES" ] || [ "$params_confirm" = "$yes" ]; then
+ echo -e " ${GREEN}Will run FunASR server later ...${PLAIN}"
+ break
+ elif [ "$params_confirm" = "$NO" ] || [ "$params_confirm" = "$no" ]; then
+ echo -e " ${RED}The parameters set are incorrect, please rerun ...${PLAIN}"
+ exit 1
+ else
+ echo "again ..."
+ fi
+ done
+
+ saveParams
+ echo
+ sleep 1
+}
+
+# Install docker
+installFunasrDocker(){
+ echo -e "${UNDERLINE}${BOLD}[4/5]${PLAIN}"
+
+ if [ $DOCKERINFOLEN -gt 30 ]; then
+ echo -e " ${YELLOW}Docker has installed.${PLAIN}"
+ else
+ lowercase_osid=$(echo ${OSID} | tr '[A-Z]' '[a-z]')
+ echo -e " ${YELLOW}Start install docker for ${lowercase_osid} ${PLAIN}"
+ DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun"
+ DOCKER_INSTALL_RUN_CMD=""
+
+ case "$lowercase_osid" in
+ ubuntu)
+ DOCKER_INSTALL_CMD="curl -fsSL https://test.docker.com -o test-docker.sh"
+ DOCKER_INSTALL_RUN_CMD="sudo sh test-docker.sh"
+ ;;
+ centos)
+ DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun"
+ ;;
+ debian)
+ DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com -o get-docker.sh"
+ DOCKER_INSTALL_RUN_CMD="sudo sh get-docker.sh"
+ ;;
+ \"alios\")
+ DOCKER_INSTALL_CMD="curl -fsSL https://get.docker.com -o get-docker.sh"
+ DOCKER_INSTALL_RUN_CMD="sudo sh get-docker.sh"
+ ;;
+ \"alinux\")
+ DOCKER_INSTALL_CMD="sudo yum -y install dnf"
+ DOCKER_INSTALL_RUN_CMD="sudo dnf -y install docker"
+ ;;
+ *)
+ echo -e " ${RED}$lowercase_osid is not supported.${PLAIN}"
+ ;;
+ esac
+
+ echo -e " Get docker installer: ${GREEN}${DOCKER_INSTALL_CMD}${PLAIN}"
+ echo -e " Get docker run: ${GREEN}${DOCKER_INSTALL_RUN_CMD}${PLAIN}"
+
+ $DOCKER_INSTALL_CMD
+ if [ ! -z "$DOCKER_INSTALL_RUN_CMD" ]; then
+ $DOCKER_INSTALL_RUN_CMD
+ fi
+ sudo systemctl start docker
+
+ DOCKERINFO=$(sudo docker info | wc -l)
+ DOCKERINFOLEN=`expr ${DOCKERINFO} + 0`
+ if [ $DOCKERINFOLEN -gt 30 ]; then
+ echo -e " ${GREEN}Docker install success, start docker server.${PLAIN}"
+ sudo systemctl start docker
+ else
+ echo -e " ${RED}Docker install failed!${PLAIN}"
+ exit 1
+ fi
+ fi
+
+ echo
+ sleep 1
+
+ # Download docker image
+ echo -e " ${YELLOW}Pull docker image(${PARAMS_DOCKER_IMAGE})...${PLAIN}"
+
+ sudo docker pull $PARAMS_DOCKER_IMAGE
+
+ echo
+ sleep 1
+}
+
+dockerRun(){
+ echo -e "${UNDERLINE}${BOLD}[5/5]${PLAIN}"
+ echo -e " ${YELLOW}Construct command and run docker ...${PLAIN}"
+
+ run_cmd="sudo docker run"
+ port_map=" -p ${PARAMS_HOST_PORT}:${PARAMS_DOCKER_PORT}"
+ dir_params=" --privileged=true"
+ dir_map_params=""
+ if [ ! -z "$PARAMS_LOCAL_ASR_DIR" ]; then
+ if [ -z "$dir_map_params" ]; then
+ dir_map_params="${dir_params} -v ${PARAMS_LOCAL_ASR_DIR}:${PARAMS_DOCKER_ASR_DIR}"
+ else
+ dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_ASR_DIR}:${PARAMS_DOCKER_ASR_DIR}"
+ fi
+ fi
+ if [ ! -z "$PARAMS_LOCAL_VAD_DIR" ]; then
+ if [ -z "$dir_map_params" ]; then
+ dir_map_params="${dir_params} -v ${PARAMS_LOCAL_VAD_DIR}:${PARAMS_DOCKER_VAD_DIR}"
+ else
+ dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_VAD_DIR}:${PARAMS_DOCKER_VAD_DIR}"
+ fi
+ fi
+ if [ ! -z "$PARAMS_LOCAL_PUNC_DIR" ]; then
+ if [ -z "$dir_map_params" ]; then
+ dir_map_params="${dir_params} -v ${PARAMS_LOCAL_PUNC_DIR}:${PARAMS_DOCKER_PUNC_DIR}"
+ else
+ dir_map_params="${dir_map_params} -v ${PARAMS_LOCAL_VAD_DIR}:${PARAMS_DOCKER_VAD_DIR}"
+ fi
+ fi
+
+ exec_params="\"exec\":\"${PARAMS_DOCKER_EXEC_PATH}\""
+ if [ ! -z "$PARAMS_ASR_ID" ]; then
+ asr_params="\"--model-dir\":\"${PARAMS_ASR_ID}\""
+ else
+ asr_params="\"--model-dir\":\"${PARAMS_DOCKER_ASR_PATH}\""
+ fi
+ if [ ! -z "$PARAMS_VAD_ID" ]; then
+ vad_params="\"--vad-dir\":\"${PARAMS_VAD_ID}\""
+ else
+ vad_params="\"--vad-dir\":\"${PARAMS_DOCKER_VAD_PATH}\""
+ fi
+ if [ ! -z "$PARAMS_PUNC_ID" ]; then
+ punc_params="\"--punc-dir\":\"${PARAMS_PUNC_ID}\""
+ else
+ punc_params="\"--punc-dir\":\"${PARAMS_DOCKER_PUNC_PATH}\""
+ fi
+ download_params="\"--download-model-dir\":\"${PARAMS_DOWNLOAD_MODEL_DIR}\""
+ if [ -z "$PARAMS_DOWNLOAD_MODEL_DIR" ]; then
+ model_params="${asr_params},${vad_params},${punc_params}"
+ else
+ model_params="${asr_params},${vad_params},${punc_params},${download_params}"
+ fi
+
+ decoder_params="\"--decoder-thread-num\":\"${PARAMS_DECODER_THREAD_NUM}\""
+ io_params="\"--io-thread-num\":\"${PARAMS_IO_THREAD_NUM}\""
+ thread_params=${decoder_params},${io_params}
+ port_params="\"--port\":\"${PARAMS_DOCKER_PORT}\""
+ crt_path="\"--certfile\":\"/workspace/FunASR/funasr/runtime/ssl_key/server.crt\""
+ key_path="\"--keyfile\":\"/workspace/FunASR/funasr/runtime/ssl_key/server.key\""
+
+ env_params=" -v ${DEFAULT_FUNASR_CONFIG_DIR}:/workspace/.config"
+ env_params=" ${env_params} --env DAEMON_SERVER_CONFIG={\"server\":[{${exec_params},${model_params},${thread_params},${port_params},${crt_path},${key_path}}]}"
+
+ run_cmd="${run_cmd}${port_map}${dir_map_params}${env_params}"
+ run_cmd="${run_cmd} -it -d ${PARAMS_DOCKER_IMAGE}"
+
+ # check Docker
+ checkDockerExist
+ result=$?
+ result=`expr ${result} + 0`
+ if [ ${result} -eq 50 ]; then
+ return 50
+ fi
+
+ rm -f ${DEFAULT_FUNASR_PROGRESS_TXT}
+ rm -f ${DEFAULT_FUNASR_SERVER_LOG}
+
+ $run_cmd
+
+ echo
+ echo -e " ${YELLOW}Loading models:${PLAIN}"
+
+ # Hide the cursor, start draw progress.
+ printf "\e[?25l"
+ while true
+ do
+ serverProgress
+ result=$?
+ stage=`expr ${result} + 0`
+ if [ ${stage} -eq 0 ]; then
+ break
+ elif [ ${stage} -gt 0 ] && [ ${stage} -lt 6 ]; then
+ sleep 0.1
+ # clear 3 lines
+ printf "\033[3A"
+ elif [ ${stage} -eq 6 ]; then
+ break
+ elif [ ${stage} -eq 98 ]; then
+ return 98
+ else
+ echo -e " ${RED}Starting FunASR server failed.${PLAIN}"
+ echo
+ # Display the cursor
+ printf "\e[?25h"
+ return 99
+ fi
+ done
+ # Display the cursor
+ printf "\e[?25h"
+
+ echo -e " ${GREEN}The service has been started.${PLAIN}"
+ echo
+
+ deploySamples
+ echo -e " ${BOLD}The sample code is already stored in the ${PLAIN}(${GREEN}${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}${PLAIN}) ."
+ echo -e " ${BOLD}If you want to see an example of how to use the client, you can run ${PLAIN}${GREEN}sudo bash funasr-runtime-deploy-offline-cpu-zh.sh client${PLAIN} ."
+ echo
+}
+
+installPythonDependencyForPython(){
+ echo -e "${YELLOW}Install Python dependent environments ...${PLAIN}"
+
+ echo -e " Export dependency of Cpp sample."
+ pre_cmd="export LD_LIBRARY_PATH=${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/cpp/libs:\$LD_LIBRARY_PATH"
+ $pre_cmd
+ echo
+
+ echo -e " Install requirements of Python sample."
+ pre_cmd="pip3 install click>=8.0.4"
+ $pre_cmd
+ echo
+
+ pre_cmd="pip3 install -r ${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/python/requirements_client.txt"
+ echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
+ $pre_cmd
+ echo
+
+ lowercase_osid=$(echo ${OSID} | tr '[A-Z]' '[a-z]')
+ case "$lowercase_osid" in
+ ubuntu)
+ pre_cmd="sudo apt-get install -y ffmpeg"
+ ;;
+ centos)
+ pre_cmd="sudo yum install -y ffmpeg"
+ ;;
+ debian)
+ pre_cmd="sudo apt-get install -y ffmpeg"
+ ;;
+ \"alios\")
+ pre_cmd="sudo yum install -y ffmpeg"
+ ;;
+ \"alinux\")
+ pre_cmd="sudo yum install -y ffmpeg"
+ ;;
+ *)
+ echo -e " ${RED}$lowercase_osid is not supported.${PLAIN}"
+ ;;
+ esac
+ echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
+ echo
+
+ pre_cmd="pip3 install ffmpeg-python"
+ echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
+ $pre_cmd
+ echo
+}
+
+deploySamples(){
+ if [ ! -d $PARAMS_FUNASR_SAMPLES_LOCAL_DIR ]; then
+ echo -e "${YELLOW}Downloading samples to${PLAIN} ${CYAN}${PARAMS_FUNASR_LOCAL_WORKSPACE}${PLAIN} ${YELLOW}...${PLAIN}"
+
+ download_cmd="curl ${DEFAULT_SAMPLES_URL} -o ${PARAMS_FUNASR_SAMPLES_LOCAL_PATH}"
+ untar_cmd="tar -zxf ${PARAMS_FUNASR_SAMPLES_LOCAL_PATH} -C ${PARAMS_FUNASR_LOCAL_WORKSPACE}"
+
+ if [ ! -f "$PARAMS_FUNASR_SAMPLES_LOCAL_PATH" ]; then
+ $download_cmd
+ fi
+ $untar_cmd
+ echo
+
+ installPythonDependencyForPython
+ echo
+ fi
+}
+
+checkDockerExist(){
+ result=$(sudo docker ps | grep ${PARAMS_DOCKER_IMAGE} | wc -l)
+ result=`expr ${result} + 0`
+ if [ ${result} -ne 0 ]; then
+ echo
+ echo -e " ${RED}Docker: ${PARAMS_DOCKER_IMAGE} has been launched, please run (${PLAIN}${GREEN}sudo bash funasr-runtime-deploy-offline-cpu-zh.sh stop${PLAIN}${RED}) to stop Docker first.${PLAIN}"
+ return 50
+ fi
+}
+
+dockerExit(){
+ echo -e " ${YELLOW}Stop docker(${PLAIN}${GREEN}${PARAMS_DOCKER_IMAGE}${PLAIN}${YELLOW}) server ...${PLAIN}"
+ sudo docker stop `sudo docker ps -a| grep ${PARAMS_DOCKER_IMAGE} | awk '{print $1}' `
+ echo
+ sleep 1
+}
+
+modelChange(){
+ model_type=$1
+ model_id=$2
+ local_flag=0
+
+ if [ -d "$model_id" ]; then
+ local_flag=1
+ else
+ local_flag=0
+ fi
+
+ result=$(echo $model_type | grep "--asr_model")
+ if [ "$result" != "" ]; then
+ if [ $local_flag -eq 0 ]; then
+ PARAMS_ASR_ID=$model_id
+ PARAMS_DOCKER_ASR_PATH=${PARAMS_DOWNLOAD_MODEL_DIR}/${PARAMS_ASR_ID}
+ PARAMS_DOCKER_ASR_DIR=$(dirname "${PARAMS_DOCKER_ASR_PATH}")
+ PARAMS_LOCAL_ASR_PATH=${PARAMS_FUNASR_LOCAL_MODELS_DIR}/${PARAMS_ASR_ID}
+ PARAMS_LOCAL_ASR_DIR=$(dirname "${PARAMS_LOCAL_ASR_PATH}")
+ else
+ PARAMS_ASR_ID=""
+ PARAMS_LOCAL_ASR_PATH=$model_id
+ if [ ! -d "$PARAMS_LOCAL_ASR_PATH" ]; then
+ echo -e " ${RED}${PARAMS_LOCAL_ASR_PATH} does not exist, please set again.${PLAIN}"
+ else
+ model_name=$(basename "${PARAMS_LOCAL_ASR_PATH}")
+ PARAMS_LOCAL_ASR_DIR=$(dirname "${PARAMS_LOCAL_ASR_PATH}")
+ middle=${PARAMS_LOCAL_ASR_DIR#*"${PARAMS_FUNASR_LOCAL_MODELS_DIR}"}
+ PARAMS_DOCKER_ASR_DIR=$PARAMS_DOWNLOAD_MODEL_DIR
+ PARAMS_DOCKER_ASR_PATH=${PARAMS_DOCKER_ASR_DIR}/${middle}/${model_name}
+ fi
+ fi
+ fi
+ result=$(echo ${model_type} | grep "--vad_model")
+ if [ "$result" != "" ]; then
+ if [ $local_flag -eq 0 ]; then
+ PARAMS_VAD_ID=$model_id
+ PARAMS_DOCKER_VAD_PATH=${PARAMS_DOWNLOAD_MODEL_DIR}/${PARAMS_VAD_ID}
+ PARAMS_DOCKER_VAD_DIR=$(dirname "${PARAMS_DOCKER_VAD_PATH}")
+ PARAMS_LOCAL_VAD_PATH=${PARAMS_FUNASR_LOCAL_MODELS_DIR}/${PARAMS_VAD_ID}
+ PARAMS_LOCAL_VAD_DIR=$(dirname "${PARAMS_LOCAL_VAD_PATH}")
+ else
+ PARAMS_VAD_ID=""
+ PARAMS_LOCAL_VAD_PATH=$model_id
+ if [ ! -d "$PARAMS_LOCAL_VAD_PATH" ]; then
+ echo -e " ${RED}${PARAMS_LOCAL_VAD_PATH} does not exist, please set again.${PLAIN}"
+ else
+ model_name=$(basename "${PARAMS_LOCAL_VAD_PATH}")
+ PARAMS_LOCAL_VAD_DIR=$(dirname "${PARAMS_LOCAL_VAD_PATH}")
+ middle=${PARAMS_LOCAL_VAD_DIR#*"${PARAMS_FUNASR_LOCAL_MODELS_DIR}"}
+ PARAMS_DOCKER_VAD_DIR=$PARAMS_DOWNLOAD_MODEL_DIR
+ PARAMS_DOCKER_VAD_PATH=${PARAMS_DOCKER_VAD_DIR}/${middle}/${model_name}
+ fi
+ fi
+ fi
+ result=$(echo $model_type | grep "--punc_model")
+ if [ "$result" != "" ]; then
+ if [ $local_flag -eq 0 ]; then
+ PARAMS_PUNC_ID=$model_id
+ PARAMS_DOCKER_PUNC_PATH=${PARAMS_DOWNLOAD_MODEL_DIR}/${PARAMS_PUNC_ID}
+ PARAMS_DOCKER_PUNC_DIR=$(dirname "${PARAMS_DOCKER_PUNC_PATH}")
+ PARAMS_LOCAL_PUNC_PATH=${PARAMS_FUNASR_LOCAL_MODELS_DIR}/${PARAMS_PUNC_ID}
+ PARAMS_LOCAL_PUNC_DIR=$(dirname "${PARAMS_LOCAL_PUNC_PATH}")
+ else
+ model_name=$(basename "${PARAMS_LOCAL_PUNC_PATH}")
+ PARAMS_LOCAL_PUNC_DIR=$(dirname "${PARAMS_LOCAL_PUNC_PATH}")
+ middle=${PARAMS_LOCAL_PUNC_DIR#*"${PARAMS_FUNASR_LOCAL_MODELS_DIR}"}
+ PARAMS_DOCKER_PUNC_DIR=$PARAMS_DOWNLOAD_MODEL_DIR
+ PARAMS_DOCKER_PUNC_PATH=${PARAMS_DOCKER_PUNC_DIR}/${middle}/${model_name}
+ fi
+ fi
+}
+
+threadNumChange() {
+ type=$1
+ val=$2
+
+ if [ -z "$val"]; then
+ num=`expr ${val} + 0`
+ if [ $num -ge 1 ] && [ $num -le 1024 ]; then
+ result=$(echo ${type} | grep "--decode_thread_num")
+ if [ "$result" != "" ]; then
+ PARAMS_DECODER_THREAD_NUM=$num
+ fi
+ result=$(echo ${type} | grep "--io_thread_num")
+ if [ "$result" != "" ]; then
+ PARAMS_IO_THREAD_NUM=$num
+ fi
+ fi
+ fi
+}
+
+portChange() {
+ type=$1
+ val=$2
+
+ if [ ! -z "$val" ]; then
+ port=`expr ${val} + 0`
+ if [ $port -ge 1 ] && [ $port -le 65536 ]; then
+ result=$(echo ${type} | grep "host_port")
+ if [ "$result" != "" ]; then
+ PARAMS_HOST_PORT=$port
+ fi
+ result=$(echo ${type} | grep "docker_port")
+ if [ "$result" != "" ]; then
+ PARAMS_DOCKER_PORT=$port
+ fi
+ fi
+ fi
+}
+
+sampleClientRun(){
+ echo -e "${YELLOW}Will download sample tools for the client to show how speech recognition works.${PLAIN}"
+
+ download_cmd="curl ${DEFAULT_SAMPLES_URL} -o ${PARAMS_FUNASR_SAMPLES_LOCAL_PATH}"
+ untar_cmd="tar -zxf ${PARAMS_FUNASR_SAMPLES_LOCAL_PATH} -C ${PARAMS_FUNASR_LOCAL_WORKSPACE}"
+
+ if [ ! -f "$PARAMS_FUNASR_SAMPLES_LOCAL_PATH" ]; then
+ $download_cmd
+ fi
+ if [ -f "$PARAMS_FUNASR_SAMPLES_LOCAL_PATH" ]; then
+ $untar_cmd
+ fi
+ if [ -d "$PARAMS_FUNASR_SAMPLES_LOCAL_DIR" ]; then
+ echo -e " Please select the client you want to run."
+ menuSelection ${SAMPLE_CLIENTS[*]}
+ result=$?
+ index=`expr ${result} - 1`
+ lang=${SAMPLE_CLIENTS[${index}]}
+ echo
+
+ server_ip="127.0.0.1"
+ echo -e " Please enter the IP of server, default(${CYAN}${server_ip}${PLAIN}): \c"
+ read server_ip
+ if [ -z "$server_ip" ]; then
+ server_ip="127.0.0.1"
+ fi
+
+ host_port=`sed '/^PARAMS_HOST_PORT=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ -z "$host_port" ]; then
+ host_port="10095"
+ fi
+ echo -e " Please enter the port of server, default(${CYAN}${host_port}${PLAIN}): \c"
+ read host_port
+ if [ -z "$host_port" ]; then
+ host_port=`sed '/^PARAMS_HOST_PORT=/!d;s/.*=//' ${DEFAULT_FUNASR_CONFIG_FILE}`
+ if [ -z "$host_port" ]; then
+ host_port="10095"
+ fi
+ fi
+
+ wav_path="${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/audio/asr_example.wav"
+ echo -e " Please enter the audio path, default(${CYAN}${wav_path}${PLAIN}): \c"
+ read WAV_PATH
+ if [ -z "$wav_path" ]; then
+ wav_path="${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/audio/asr_example.wav"
+ fi
+
+ echo
+ pre_cmd=鈥濃��
+ case "$lang" in
+ Linux_Cpp)
+ pre_cmd="export LD_LIBRARY_PATH=${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/cpp/libs:\$LD_LIBRARY_PATH"
+ client_exec="${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/cpp/funasr-wss-client"
+ run_cmd="${client_exec} --server-ip ${server_ip} --port ${host_port} --wav-path ${wav_path}"
+ echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
+ $pre_cmd
+ echo
+ ;;
+ Python)
+ client_exec="${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/python/wss_client_asr.py"
+ run_cmd="python3 ${client_exec} --host ${server_ip} --port ${host_port} --mode offline --audio_in ${wav_path} --send_without_sleep --output_dir ${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/python"
+ pre_cmd="pip3 install click>=8.0.4"
+ echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
+ $pre_cmd
+ echo
+ pre_cmd="pip3 install -r ${PARAMS_FUNASR_SAMPLES_LOCAL_DIR}/python/requirements_client.txt"
+ echo -e " Run ${BLUE}${pre_cmd}${PLAIN}"
+ $pre_cmd
+ echo
+ ;;
+ *)
+ echo "${lang} is not supported."
+ ;;
+ esac
+
+ echo -e " Run ${BLUE}${run_cmd}${PLAIN}"
+ $run_cmd
+ echo
+ echo -e " If failed, you can try (${GREEN}${run_cmd}${PLAIN}) in your Shell."
+ echo
+ fi
+}
+
+paramsConfigure(){
+ initConfiguration
+ initParameters
+ selectDockerImages
+ result=$?
+ result=`expr ${result} + 0`
+ if [ ${result} -eq 50 ]; then
+ return 50
+ fi
+
+ setupHostPort
+ complementParameters
+}
+
+# Display Help info
+displayHelp(){
+ echo -e "${UNDERLINE}Usage${PLAIN}:"
+ echo -e " $0 [OPTIONAL FLAGS]"
+ echo
+ echo -e "funasr-runtime-deploy-offline-cpu-zh.sh - a Bash script to install&run FunASR docker."
+ echo
+ echo -e "${UNDERLINE}Options${PLAIN}:"
+ echo -e " ${BOLD}-i, install, --install${PLAIN} Install and run FunASR docker."
+ echo -e " install [--workspace] <workspace in local>"
+ echo -e " ${BOLD}-s, start , --start${PLAIN} Run FunASR docker with configuration that has already been set."
+ echo -e " ${BOLD}-p, stop , --stop${PLAIN} Stop FunASR docker."
+ echo -e " ${BOLD}-r, restart, --restart${PLAIN} Restart FunASR docker."
+ echo -e " ${BOLD}-u, update , --update${PLAIN} Update parameters that has already been set."
+ echo -e " update [--workspace] <workspace in local>"
+ echo -e " update [--asr_model | --vad_model | --punc_model] <model_id or local model path>"
+ echo -e " update [--host_port | --docker_port] <port number>"
+ echo -e " update [--decode_thread_num | io_thread_num] <the number of threads>"
+ echo -e " ${BOLD}-c, client , --client${PLAIN} Get a client example to show how to initiate speech recognition."
+ echo -e " ${BOLD}-o, show , --show${PLAIN} Displays all parameters that have been set."
+ echo -e " ${BOLD}-v, version, --version${PLAIN} Display current script version."
+ echo -e " ${BOLD}-h, help , --help${PLAIN} Display this help."
+ echo
+ echo -e " Version : ${scriptVersion} "
+ echo -e " Modify Date: ${scriptDate}"
+}
+
+parseInput(){
+ local menu
+ menu=($(echo "$@"))
+ len=${#menu[@]}
+
+ stage=""
+ if [ $len -ge 2 ]; then
+ for val in ${menu[@]}
+ do
+ result=$(echo $val | grep "\-\-")
+ if [ "$result" != "" ]; then
+ stage=$result
+ else
+ if [ "$stage" = "--workspace" ]; then
+ relativePathToFullPath $val
+ PARAMS_FUNASR_LOCAL_WORKSPACE=$full_path
+ if [ ! -z "$PARAMS_FUNASR_LOCAL_WORKSPACE" ]; then
+ mkdir -p $PARAMS_FUNASR_LOCAL_WORKSPACE
+ fi
+ fi
+ fi
+ done
+ fi
+}
+
+# OS
+OSID=$(grep ^ID= /etc/os-release | cut -d= -f2)
+OSVER=$(lsb_release -cs)
+OSNUM=$(grep -oE "[0-9.]+" /etc/issue)
+CPUNUM=$(cat /proc/cpuinfo |grep "processor"|wc -l)
+DOCKERINFO=$(sudo docker info | wc -l)
+DOCKERINFOLEN=`expr ${DOCKERINFO} + 0`
+
+# PARAMS
+# The workspace for FunASR in local
+PARAMS_FUNASR_LOCAL_WORKSPACE=$DEFAULT_FUNASR_LOCAL_WORKSPACE
+# The dir stored sample code in local
+PARAMS_FUNASR_SAMPLES_LOCAL_DIR=${PARAMS_FUNASR_LOCAL_WORKSPACE}/${DEFAULT_SAMPLES_DIR}
+# The path of sample code in local
+PARAMS_FUNASR_SAMPLES_LOCAL_PATH=${PARAMS_FUNASR_LOCAL_WORKSPACE}/${DEFAULT_SAMPLES_NAME}.tar.gz
+# The dir stored models in local
+PARAMS_FUNASR_LOCAL_MODELS_DIR="${PARAMS_FUNASR_LOCAL_WORKSPACE}/models"
+# The path of configuration in local
+PARAMS_FUNASR_CONFIG_PATH="${PARAMS_FUNASR_LOCAL_WORKSPACE}/config"
+
+# The server excutor in local
+PARAMS_DOCKER_EXEC_PATH=$DEFAULT_DOCKER_EXEC_PATH
+# The dir stored server excutor in docker
+PARAMS_DOCKER_EXEC_DIR=$DEFAULT_DOCKER_EXEC_DIR
+
+# The dir for downloading model in docker
+PARAMS_DOWNLOAD_MODEL_DIR=$DEFAULT_FUNASR_WORKSPACE_DIR
+# The Docker image name
+PARAMS_DOCKER_IMAGE=""
+
+# The dir stored punc model in local
+PARAMS_LOCAL_PUNC_DIR=""
+# The path of punc model in local
+PARAMS_LOCAL_PUNC_PATH=""
+# The dir stored punc model in docker
+PARAMS_DOCKER_PUNC_DIR=""
+# The path of punc model in docker
+PARAMS_DOCKER_PUNC_PATH=""
+# The punc model ID in ModelScope
+PARAMS_PUNC_ID="damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx"
+
+# The dir stored vad model in local
+PARAMS_LOCAL_VAD_DIR=""
+# The path of vad model in local
+PARAMS_LOCAL_VAD_PATH=""
+# The dir stored vad model in docker
+PARAMS_DOCKER_VAD_DIR=""
+# The path of vad model in docker
+PARAMS_DOCKER_VAD_PATH=""
+# The vad model ID in ModelScope
+PARAMS_VAD_ID="damo/speech_fsmn_vad_zh-cn-16k-common-onnx"
+
+# The dir stored asr model in local
+PARAMS_LOCAL_ASR_DIR=""
+# The path of asr model in local
+PARAMS_LOCAL_ASR_PATH=""
+# The dir stored asr model in docker
+PARAMS_DOCKER_ASR_DIR=""
+# The path of asr model in docker
+PARAMS_DOCKER_ASR_PATH=""
+# The asr model ID in ModelScope
+PARAMS_ASR_ID="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx"
+
+PARAMS_HOST_PORT="10095"
+PARAMS_DOCKER_PORT="10095"
+PARAMS_DECODER_THREAD_NUM="32"
+PARAMS_IO_THREAD_NUM="8"
+
+
+echo -e "#############################################################"
+echo -e "# ${RED}OS${PLAIN}: ${OSID} ${OSNUM} ${OSVER}"
+echo -e "# ${RED}Kernel${PLAIN}: $(uname -m) Linux $(uname -r)"
+echo -e "# ${RED}CPU${PLAIN}: $(grep 'model name' /proc/cpuinfo | uniq | awk -F : '{print $2}' | sed 's/^[ \t]*//g' | sed 's/ \+/ /g') "
+echo -e "# ${RED}CPU NUM${PLAIN}: ${CPUNUM}"
+echo -e "# ${RED}RAM${PLAIN}: $(cat /proc/meminfo | grep 'MemTotal' | awk -F : '{print $2}' | sed 's/^[ \t]*//g') "
+echo -e "#"
+echo -e "# ${RED}Version${PLAIN}: ${scriptVersion} "
+echo -e "# ${RED}Modify Date${PLAIN}: ${scriptDate}"
+echo -e "#############################################################"
+echo
+
+# Initialization step
+case "$1" in
+ install|-i|--install)
+ rootNess
+ paramsFromDefault
+ parseInput $@
+ paramsConfigure
+ result=$?
+ result=`expr ${result} + 0`
+ if [ ${result} -ne 50 ]; then
+ showAllParams
+ installFunasrDocker
+ dockerRun
+ result=$?
+ stage=`expr ${result} + 0`
+ if [ $stage -eq 98 ]; then
+ dockerExit
+ dockerRun
+ fi
+ fi
+ ;;
+ start|-s|--start)
+ rootNess
+ paramsFromDefault
+ showAllParams
+ dockerRun
+ result=$?
+ stage=`expr ${result} + 0`
+ if [ $stage -eq 98 ]; then
+ dockerExit
+ dockerRun
+ fi
+ ;;
+ restart|-r|--restart)
+ rootNess
+ paramsFromDefault
+ showAllParams
+ dockerExit
+ dockerRun
+ result=$?
+ stage=`expr ${result} + 0`
+ if [ $stage -eq 98 ]; then
+ dockerExit
+ dockerRun
+ fi
+ ;;
+ stop|-p|--stop)
+ rootNess
+ paramsFromDefault
+ dockerExit
+ ;;
+ update|-u|--update)
+ rootNess
+ paramsFromDefault
+
+ if [ $# -eq 3 ]; then
+ type=$2
+ val=$3
+ if [ "$type" = "--asr_model" ] || [ "$type" = "--vad_model" ] || [ "$type" = "--punc_model" ]; then
+ modelChange $type $val
+ elif [ "$type" = "--decode_thread_num" ] || [ "$type" = "--io_thread_num" ]; then
+ threadNumChange $type $val
+ elif [ "$type" = "--host_port" ] || [ "$type" = "--docker_port" ]; then
+ portChange $type $val
+ elif [ "$type" = "--workspace" ]; then
+ relativePathToFullPath $val
+ PARAMS_FUNASR_LOCAL_WORKSPACE=$full_path
+ if [ ! -z "$PARAMS_FUNASR_LOCAL_WORKSPACE" ]; then
+ mkdir -p $PARAMS_FUNASR_LOCAL_WORKSPACE
+ fi
+ else
+ displayHelp
+ fi
+ else
+ displayHelp
+ fi
+
+ initParameters
+ complementParameters
+ showAllParams
+ dockerExit
+ dockerRun
+ result=$?
+ stage=`expr ${result} + 0`
+ if [ $stage -eq 98 ]; then
+ dockerExit
+ dockerRun
+ fi
+ ;;
+ client|-c|--client)
+ rootNess
+ paramsFromDefault
+ parseInput $@
+ sampleClientRun
+ ;;
+ show|-o|--show)
+ rootNess
+ paramsFromDefault
+ showAllParams
+ ;;
+ *)
+ displayHelp
+ exit 0
+ ;;
+esac
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline.md b/funasr/runtime/docs/SDK_advanced_guide_offline.md
new file mode 100644
index 0000000..6dd468d
--- /dev/null
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline.md
@@ -0,0 +1,259 @@
+ # Advanced Development Guide (File transcription service)
+
+FunASR provides a Chinese offline file transcription service that can be deployed locally or on a cloud server with just one click. The core of the service is the FunASR runtime SDK, which has been open-sourced. FunASR-runtime combines various capabilities such as speech endpoint detection (VAD), large-scale speech recognition (ASR) using Paraformer-large, and punctuation detection (PUNC), which have all been open-sourced by the speech laboratory of DAMO Academy on the Modelscope community. This enables accurate and efficient high-concurrency transcription of audio files.
+
+This document serves as a development guide for the FunASR offline file transcription service. If you wish to quickly experience the offline file transcription service, please refer to the one-click deployment example for the FunASR offline file transcription service ([docs](./SDK_tutorial.md)).
+
+## Installation of Docker
+
+The following steps are for manually installing Docker and Docker images. If your Docker image has already been launched, you can ignore this step.
+
+### Installation of Docker environment
+
+```shell
+# Ubuntu锛�
+curl -fsSL https://test.docker.com -o test-docker.sh
+sudo sh test-docker.sh
+# Debian锛�
+curl -fsSL https://get.docker.com -o get-docker.sh
+sudo sh get-docker.sh
+# CentOS锛�
+curl -fsSL https://get.docker.com | bash -s docker --mirror Aliyun
+# MacOS锛�
+brew install --cask --appdir=/Applications docker
+```
+
+More details could ref to [docs](https://alibaba-damo-academy.github.io/FunASR/en/installation/docker.html)
+
+### Starting Docker
+
+```shell
+sudo systemctl start docker
+```
+
+### Pulling and launching images
+
+Use the following command to pull and launch the Docker image for the FunASR runtime-SDK:
+
+```shell
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
+
+sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
+```
+
+Introduction to command parameters:
+```text
+-p <host port>:<mapped docker port>: In the example, host machine (ECS) port 10095 is mapped to port 10095 in the Docker container. Make sure that port 10095 is open in the ECS security rules.
+
+-v <host path>:<mounted Docker path>: In the example, the host machine path /root is mounted to the Docker path /workspace/models.
+
+```
+
+
+## Starting the server
+
+Use the flollowing script to start the server 锛�
+```shell
+./run_server.sh --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
+```
+
+More details about the script run_server.sh:
+
+The FunASR-wss-server supports downloading models from Modelscope. You can set the model download address (--download-model-dir, default is /workspace/models) and the model ID (--model-dir, --vad-dir, --punc-dir). Here is an example:
+
+```shell
+cd /workspace/FunASR/funasr/runtime/websocket/build/bin
+./funasr-wss-server \
+ --download-model-dir /workspace/models \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \
+ --decoder-thread-num 32 \
+ --io-thread-num 8 \
+ --port 10095 \
+ --certfile ../../../ssl_key/server.crt \
+ --keyfile ../../../ssl_key/server.key
+ ```
+
+Introduction to command parameters:
+
+```text
+--download-model-dir: Model download address, download models from Modelscope by setting the model ID.
+--model-dir: Modelscope model ID.
+--quantize: True for quantized ASR model, False for non-quantized ASR model. Default is True.
+--vad-dir: Modelscope model ID.
+--vad-quant: True for quantized VAD model, False for non-quantized VAD model. Default is True.
+--punc-dir: Modelscope model ID.
+--punc-quant: True for quantized PUNC model, False for non-quantized PUNC model. Default is True.
+--port: Port number that the server listens on. Default is 10095.
+--decoder-thread-num: Number of inference threads that the server starts. Default is 8.
+--io-thread-num: Number of IO threads that the server starts. Default is 1.
+--certfile <string>: SSL certificate file. Default is ../../../ssl_key/server.crt.
+--keyfile <string>: SSL key file. Default is ../../../ssl_key/server.key.
+```
+
+The FunASR-wss-server also supports loading models from a local path (see Preparing Model Resources for detailed instructions on preparing local model resources). Here is an example:
+
+```shell
+cd /workspace/FunASR/funasr/runtime/websocket/build/bin
+./funasr-wss-server \
+ --model-dir /workspace/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --vad-dir /workspace/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --punc-dir /workspace/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx \
+ --decoder-thread-num 32 \
+ --io-thread-num 8 \
+ --port 10095 \
+ --certfile ../../../ssl_key/server.crt \
+ --keyfile ../../../ssl_key/server.key
+ ```
+
+
+## Preparing Model Resources
+
+If you choose to download models from Modelscope through the FunASR-wss-server, you can skip this step. The vad, asr, and punc model resources in the offline file transcription service of FunASR are all from Modelscope. The model addresses are shown in the table below:
+
+| Model | Modelscope url |
+|-------|------------------------------------------------------------------------------------------------------------------|
+| VAD | https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary |
+| ASR | https://www.modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/summary |
+| PUNC | https://www.modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/summary |
+
+The offline file transcription service deploys quantized ONNX models. Below are instructions on how to export ONNX models and their quantization. You can choose to export ONNX models from Modelscope, local files, or finetuned resources:
+
+### Exporting ONNX models from Modelscope
+
+Download the corresponding model with the given model name from the Modelscope website, and then export the quantized ONNX model
+
+```shell
+python -m funasr.export.export_model \
+--export-dir ./export \
+--type onnx \
+--quantize True \
+--model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch \
+--model-name damo/speech_fsmn_vad_zh-cn-16k-common-pytorch \
+--model-name damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch
+```
+
+Introduction to command parameters:
+
+```text
+--model-name: The name of the model on Modelscope, for example: damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
+--export-dir: The export directory of ONNX model.
+--type: Model type, currently supports ONNX and torch.
+--quantize: Quantize the int8 model.
+```
+
+### Exporting ONNX models from local files
+
+Set the model name to the local path of the model, and export the quantized ONNX model:
+
+```shell
+python -m funasr.export.export_model --model-name /workspace/models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
+```
+
+
+### Exporting models from finetuned resources
+
+If you want to deploy a finetuned model, you can follow these steps:
+Rename the model you want to deploy after finetuning (for example, 10epoch.pb) to model.pb, and replace the original model.pb in Modelscope with this one. If the path of the replaced model is /path/to/finetune/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch, use the following command to convert the finetuned model to an ONNX model:
+
+```shell
+python -m funasr.export.export_model --model-name /path/to/finetune/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
+```
+
+## Starting the client
+
+After completing the deployment of FunASR offline file transcription service on the server, you can test and use the service by following these steps. Currently, FunASR-bin supports multiple ways to start the client. The following are command-line examples based on python-client, c++-client, and custom client Websocket communication protocol:
+
+### python-client
+```shell
+python wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
+```
+
+Introduction to command parameters:
+
+```text
+--host: the IP address of the server. It can be set to 127.0.0.1 for local testing.
+--port: the port number of the server listener.
+--audio_in: the audio input. Input can be a path to a wav file or a wav.scp file (a Kaldi-formatted wav list in which each line includes a wav_id followed by a tab and a wav_path).
+--output_dir: the path to the recognition result output.
+--ssl: whether to use SSL encryption. The default is to use SSL.
+--mode: offline mode.
+```
+
+### c++-client
+```shell
+. /funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path test.wav --thread-num 1 --is-ssl 1
+```
+
+Introduction to command parameters:
+
+```text
+--host: the IP address of the server. It can be set to 127.0.0.1 for local testing.
+--port: the port number of the server listener.
+--audio_in: the audio input. Input can be a path to a wav file or a wav.scp file (a Kaldi-formatted wav list in which each line includes a wav_id followed by a tab and a wav_path).
+--output_dir: the path to the recognition result output.
+--ssl: whether to use SSL encryption. The default is to use SSL.
+--mode: offline mode.
+```
+
+### Custom client
+
+If you want to define your own client, the Websocket communication protocol is as follows:
+
+```text
+# First communication
+{"mode": "offline", "wav_name": wav_name, "is_speaking": True}
+# Send wav data
+Bytes data
+# Send end flag
+{"is_speaking": False}
+```
+
+## How to customize service deployment
+
+The code for FunASR-runtime is open source. If the server and client cannot fully meet your needs, you can further develop them based on your own requirements:
+
+### C++ client
+
+https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/websocket
+
+### Python client
+
+https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/websocket
+
+### C++ server
+
+#### VAD
+```c++
+// The use of the VAD model consists of two steps: FsmnVadInit and FsmnVadInfer:
+FUNASR_HANDLE vad_hanlde=FsmnVadInit(model_path, thread_num);
+// Where: model_path contains "model-dir" and "quantize", thread_num is the ONNX thread count;
+FUNASR_RESULT result=FsmnVadInfer(vad_hanlde, wav_file.c_str(), NULL, 16000);
+// Where: vad_hanlde is the return value of FunOfflineInit, wav_file is the path to the audio file, and sampling_rate is the sampling rate (default 16k).
+```
+
+See the usage example for details [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/onnxruntime/bin/funasr-onnx-offline-vad.cpp)
+
+#### ASR
+```text
+// The use of the ASR model consists of two steps: FunOfflineInit and FunOfflineInfer:
+FUNASR_HANDLE asr_hanlde=FunOfflineInit(model_path, thread_num);
+// Where: model_path contains "model-dir" and "quantize", thread_num is the ONNX thread count;
+FUNASR_RESULT result=FunOfflineInfer(asr_hanlde, wav_file.c_str(), RASR_NONE, NULL, 16000);
+// Where: asr_hanlde is the return value of FunOfflineInit, wav_file is the path to the audio file, and sampling_rate is the sampling rate (default 16k).
+```
+
+See the usage example for details, [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/onnxruntime/bin/funasr-onnx-offline.cpp)
+
+#### PUNC
+```text
+// The use of the PUNC model consists of two steps: CTTransformerInit and CTTransformerInfer:
+FUNASR_HANDLE punc_hanlde=CTTransformerInit(model_path, thread_num);
+// Where: model_path contains "model-dir" and "quantize", thread_num is the ONNX thread count;
+FUNASR_RESULT result=CTTransformerInfer(punc_hanlde, txt_str.c_str(), RASR_NONE, NULL);
+// Where: punc_hanlde is the return value of CTTransformerInit, txt_str is the text
+```
+See the usage example for details, [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/onnxruntime/bin/funasr-onnx-offline-punc.cpp)
diff --git a/funasr/runtime/docs/SDK_advanced_guide_cn.md b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
similarity index 96%
rename from funasr/runtime/docs/SDK_advanced_guide_cn.md
rename to funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
index 534375c..2610d6f 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_cn.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline_zh.md
@@ -35,9 +35,9 @@
閫氳繃涓嬭堪鍛戒护鎷夊彇骞跺惎鍔‵unASR runtime-SDK鐨刣ocker闀滃儚锛�
```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.0.1
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
-sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.0.1
+sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
```
鍛戒护鍙傛暟浠嬬粛锛�
@@ -52,6 +52,13 @@
## 鏈嶅姟绔惎鍔�
docker鍚姩涔嬪悗锛屽惎鍔� funasr-wss-server鏈嶅姟绋嬪簭锛�
+```shell
+./run_server.sh --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+ --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+ --punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
+```
+
+璇︾粏鍛戒护鍙傛暟浠嬬粛锛�
funasr-wss-server鏀寔浠嶮odelscope涓嬭浇妯″瀷锛岃缃ā鍨嬩笅杞藉湴鍧�锛�--download-model-dir锛岄粯璁や负/workspace/models锛夊強model ID锛�--model-dir銆�--vad-dir銆�--punc-dir锛�,绀轰緥濡備笅锛�
```shell
diff --git a/funasr/runtime/docs/SDK_tutorial.md b/funasr/runtime/docs/SDK_tutorial.md
index a4e46f1..0943466 100644
--- a/funasr/runtime/docs/SDK_tutorial.md
+++ b/funasr/runtime/docs/SDK_tutorial.md
@@ -8,10 +8,14 @@
### Downloading Tools and Deployment
-Run the following command to perform a one-click deployment of the FunASR runtime-SDK service. Follow the prompts to complete the deployment and running of the service. Currently, only Linux environments are supported, and for other environments, please refer to the Advanced SDK Development Guide. Due to network restrictions, the download of the funasr-runtime-deploy.sh one-click deployment tool may not proceed smoothly. If the tool has not been downloaded and entered into the one-click deployment tool after several seconds, please terminate it with Ctrl + C and run the following command again.
+Run the following command to perform a one-click deployment of the FunASR runtime-SDK service. Follow the prompts to complete the deployment and running of the service. Currently, only Linux environments are supported, and for other environments, please refer to the Advanced SDK Development Guide ([docs](./SDK_advanced_guide_offline.md)).
+
+[//]: # (Due to network restrictions, the download of the funasr-runtime-deploy.sh one-click deployment tool may not proceed smoothly. If the tool has not been downloaded and entered into the one-click deployment tool after several seconds, please terminate it with Ctrl + C and run the following command again.)
```shell
curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR-APP/main/TransAudio/funasr-runtime-deploy.sh; sudo bash funasr-runtime-deploy.sh install
+# For the users in China, you could install with the command:
+# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy.sh; sudo bash funasr-runtime-deploy.sh install
```
#### Details of Configuration
diff --git a/funasr/runtime/docs/SDK_tutorial_cn.md b/funasr/runtime/docs/SDK_tutorial_cn.md
deleted file mode 100644
index a465501..0000000
--- a/funasr/runtime/docs/SDK_tutorial_cn.md
+++ /dev/null
@@ -1,327 +0,0 @@
-# FunASR绂荤嚎鏂囦欢杞啓鏈嶅姟渚挎嵎閮ㄧ讲鏁欑▼
-
-FunASR鎻愪緵鍙究鎹锋湰鍦版垨鑰呬簯绔湇鍔″櫒閮ㄧ讲鐨勭绾挎枃浠惰浆鍐欐湇鍔★紝鍐呮牳涓篎unASR宸插紑婧恟untime-SDK銆傞泦鎴愪簡杈炬懇闄㈣闊冲疄楠屽鍦∕odelscope绀惧尯寮�婧愮殑璇煶绔偣妫�娴�(VAD)銆丳araformer-large璇煶璇嗗埆(ASR)銆佹爣鐐规仮澶�(PUNC) 绛夌浉鍏宠兘鍔涳紝鍙互鍑嗙‘銆侀珮鏁堢殑瀵归煶棰戣繘琛岄珮骞跺彂杞啓銆�
-
-## 鐜瀹夎涓庡惎鍔ㄦ湇鍔�
-
-鏈嶅姟鍣ㄩ厤缃笌鐢宠锛堝厤璐硅瘯鐢�1锝�3涓湀锛夛紙[鐐瑰嚮姝ゅ](./aliyun_server_tutorial.md)锛�
-### 鑾峰緱鑴氭湰宸ュ叿骞朵竴閿儴缃�
-
-閫氳繃浠ヤ笅鍛戒护杩愯涓�閿儴缃叉湇鍔★紝鎸夌収鎻愮ず閫愭瀹屾垚FunASR runtime-SDK鏈嶅姟鐨勯儴缃插拰杩愯銆傜洰鍓嶆殏鏃朵粎鏀寔Linux鐜锛屽叾浠栫幆澧冨弬鑰冩枃妗楂橀樁寮�鍙戞寚鍗梋(./SDK_advanced_guide_cn.md)銆�
-鍙楅檺浜庣綉缁滐紝funasr-runtime-deploy.sh涓�閿儴缃插伐鍏风殑涓嬭浇鍙兘涓嶉『鍒╋紝閬囧埌鏁扮杩樻湭涓嬭浇杩涘叆涓�閿儴缃插伐鍏风殑鎯呭喌锛岃Ctrl + C 缁堟鍚庡啀娆¤繍琛屼互涓嬪懡浠ゃ��
-
-```shell
-curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR-APP/main/TransAudio/funasr-runtime-deploy.sh; sudo bash funasr-runtime-deploy.sh install
-```
-
-#### 鍚姩杩囩▼閰嶇疆璇﹁В
-
-##### 閫夋嫨FunASR Docker闀滃儚
-鎺ㄨ崘閫夋嫨latest浣跨敤鎴戜滑鐨勬渶鏂伴暅鍍忥紝涔熷彲閫夋嫨鍘嗗彶鐗堟湰銆�
-```text
-[1/9]
- Please choose the Docker image.
- 1) registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
- 2) registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0
- Enter your choice: 1
- You have chosen the Docker image: registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
-```
-
-##### 閫夋嫨ASR/VAD/PUNC妯″瀷
-
-浣犲彲浠ラ�夋嫨ModelScope涓殑妯″瀷锛屼篃鍙互閫�<model_name>鑷濉叆ModelScope涓殑妯″瀷鍚嶏紝灏嗕細鍦―ocker杩愯鏃惰嚜鍔ㄤ笅杞姐�傚悓鏃朵篃鍙互閫夋嫨<model_path>濉叆瀹夸富鏈轰腑鐨勬湰鍦版ā鍨嬭矾寰勩��
-
-```text
-[2/9]
- Please input [Y/n] to confirm whether to automatically download model_id in ModelScope or use a local model.
- [y] With the model in ModelScope, the model will be automatically downloaded to Docker(/workspace/models).
- If you select both the local model and the model in ModelScope, select [y].
- [n] Use the models on the localhost, the directory where the model is located will be mapped to Docker.
- Setting confirmation[Y/n]:
- You have chosen to use the model in ModelScope, please set the model ID in the next steps, and the model will be automatically downloaded in (/workspace/models) during the run.
-
- Please enter the local path to download models, the corresponding path in Docker is /workspace/models.
- Setting the local path to download models, default(/root/models):
- The local path(/root/models) set will store models during the run.
-
- [2.1/9]
- Please select ASR model_id in ModelScope from the list below.
- 1) damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
- 2) model_name
- 3) model_path
- Enter your choice: 1
- The model ID is damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
- The model dir in Docker is /workspace/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
-
- [2.2/9]
- Please select VAD model_id in ModelScope from the list below.
- 1) damo/speech_fsmn_vad_zh-cn-16k-common-onnx
- 2) model_name
- 3) model_path
- Enter your choice: 1
- The model ID is damo/speech_fsmn_vad_zh-cn-16k-common-onnx
- The model dir in Docker is /workspace/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx
-
- [2.3/9]
- Please select PUNC model_id in ModelScope from the list below.
- 1) damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
- 2) model_name
- 3) model_path
- Enter your choice: 1
- The model ID is damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
- The model dir in Docker is /workspace/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
-```
-
-##### 杈撳叆瀹夸富鏈轰腑FunASR鏈嶅姟鍙墽琛岀▼搴忚矾寰�
-
-杈撳叆FunASR鏈嶅姟鍙墽琛岀▼搴忕殑瀹夸富鏈鸿矾寰勶紝Docker杩愯鏃跺皢鑷姩鎸傝浇鍒癉ocker涓繍琛屻�傞粯璁や笉杈撳叆鐨勬儏鍐典笅灏嗘寚瀹欴ocker涓粯璁ょ殑/workspace/FunASR/funasr/runtime/websocket/build/bin/funasr-wss-server銆�
-
-```text
-[3/9]
- Please enter the path to the excutor of the FunASR service on the localhost.
- If not set, the default /workspace/FunASR/funasr/runtime/websocket/build/bin/funasr-wss-server in Docker is used.
- Setting the path to the excutor of the FunASR service on the localhost:
- Corresponding, the path of FunASR in Docker is /workspace/FunASR/funasr/runtime/websocket/build/bin/funasr-wss-server
-```
-
-##### 璁剧疆瀹夸富鏈烘彁渚涚粰FunASR鐨勭鍙�
-璁剧疆鎻愪緵缁橠ocker鐨勫涓绘満绔彛锛岄粯璁や负10095銆傝淇濊瘉姝ょ鍙ｅ彲鐢ㄣ��
-```text
-[4/9]
- Please input the opened port in the host used for FunASR server.
- Default: 10095
- Setting the opened host port [1-65535]:
- The port of the host is 10095
- The port in Docker for FunASR server is 10095
-```
-
-
-##### 璁剧疆FunASR鏈嶅姟鐨勬帹鐞嗙嚎绋嬫暟
-璁剧疆FunASR鏈嶅姟鐨勬帹鐞嗙嚎绋嬫暟锛岄粯璁や负瀹夸富鏈烘牳鏁帮紝鍚屾椂鑷姩璁剧疆鏈嶅姟鐨処O绾跨▼鏁帮紝涓烘帹鐞嗙嚎绋嬫暟鐨勫洓鍒嗕箣涓�銆�
-```text
-[5/9]
- Please input thread number for FunASR decoder.
- Default: 1
- Setting the number of decoder thread:
-
- The number of decoder threads is 1
- The number of IO threads is 1
-```
-
-##### 鎵�鏈夎缃弬鏁板睍绀哄強纭
-
-灞曠ず鍓嶉潰6姝ヨ缃殑鍙傛暟锛岀‘璁ゅ垯灏嗘墍鏈夊弬鏁板瓨鍌ㄥ埌/var/funasr/config锛屽苟寮�濮嬪惎鍔―ocker锛屽惁鍒欐彁绀虹敤鎴疯繘琛岄噸鏂拌缃��
-
-```text
-
-[6/9]
- Show parameters of FunASR server setting and confirm to run ...
-
- The current Docker image is : registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
- The model is downloaded or stored to this directory in local : /root/models
- The model will be automatically downloaded to the directory : /workspace/models
- The ASR model_id used : damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
- The ASR model directory corresponds to the directory in Docker : /workspace/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
- The VAD model_id used : damo/speech_fsmn_vad_zh-cn-16k-common-onnx
- The VAD model directory corresponds to the directory in Docker : /workspace/models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx
- The PUNC model_id used : damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
- The PUNC model directory corresponds to the directory in Docker: /workspace/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
-
- The path in the docker of the FunASR service executor : /workspace/FunASR/funasr/runtime/websocket/build/bin/funasr-wss-server
- Set the host port used for use by the FunASR service : 10095
- Set the docker port used by the FunASR service : 10095
- Set the number of threads used for decoding the FunASR service : 1
- Set the number of threads used for IO the FunASR service : 1
-
- Please input [Y/n] to confirm the parameters.
- [y] Verify that these parameters are correct and that the service will run.
- [n] The parameters set are incorrect, it will be rolled out, please rerun.
- read confirmation[Y/n]:
-
- Will run FunASR server later ...
- Parameters are stored in the file /var/funasr/config
-```
-
-##### 妫�鏌ocker鏈嶅姟
-
-妫�鏌ュ綋鍓嶅涓绘満鏄惁瀹夎浜咲ocker鏈嶅姟锛岃嫢鏈畨瑁咃紝鍒欏畨瑁匘ocker骞跺惎鍔ㄣ��
-
-```text
-[7/9]
- Start install docker for ubuntu
- Get docker installer: curl -fsSL https://test.docker.com -o test-docker.sh
- Get docker run: sudo sh test-docker.sh
-# Executing docker install script, commit: c2de0811708b6d9015ed1a2c80f02c9b70c8ce7b
-+ sh -c apt-get update -qq >/dev/null
-+ sh -c DEBIAN_FRONTEND=noninteractive apt-get install -y -qq apt-transport-https ca-certificates curl >/dev/null
-+ sh -c install -m 0755 -d /etc/apt/keyrings
-+ sh -c curl -fsSL "https://download.docker.com/linux/ubuntu/gpg" | gpg --dearmor --yes -o /etc/apt/keyrings/docker.gpg
-+ sh -c chmod a+r /etc/apt/keyrings/docker.gpg
-+ sh -c echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu focal test" > /etc/apt/sources.list.d/docker.list
-+ sh -c apt-get update -qq >/dev/null
-+ sh -c DEBIAN_FRONTEND=noninteractive apt-get install -y -qq docker-ce docker-ce-cli containerd.io docker-compose-plugin docker-ce-rootless-extras docker-buildx-plugin >/dev/null
-+ sh -c docker version
-Client: Docker Engine - Community
- Version: 24.0.2
-
- ...
- ...
-
- Docker install success, start docker server.
-```
-
-##### 涓嬭浇FunASR Docker闀滃儚
-
-涓嬭浇骞舵洿鏂皊tep1.1涓�夋嫨鐨凢unASR Docker闀滃儚銆�
-
-```text
-[8/9]
- Pull docker image(registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest)...
-funasr-runtime-cpu-0.0.1: Pulling from funasr_repo/funasr
-7608715873ec: Pull complete
-3e1014c56f38: Pull complete
-
- ...
- ...
-```
-
-##### 鍚姩FunASR Docker
-
-鍚姩FunASR Docker锛岀瓑寰卻tep1.2閫夋嫨鐨勬ā鍨嬩笅杞藉畬鎴愬苟鍚姩FunASR鏈嶅姟銆�
-
-```text
-[9/9]
- Construct command and run docker ...
-943d8f02b4e5011b71953a0f6c1c1b9bc5aff63e5a96e7406c83e80943b23474
-
- Loading models:
- [ASR ][Done ][==================================================][100%][1.10MB/s][v1.2.1]
- [VAD ][Done ][==================================================][100%][7.26MB/s][v1.2.0]
- [PUNC][Done ][==================================================][100%][ 474kB/s][v1.1.7]
- The service has been started.
- If you want to see an example of how to use the client, you can run sudo bash funasr-runtime-deploy.sh -c .
-```
-
-#### 鍚姩宸茬粡閮ㄧ讲杩囩殑FunASR鏈嶅姟
-涓�閿儴缃插悗鑻ュ嚭鐜伴噸鍚數鑴戠瓑鍏抽棴Docker鐨勫姩浣滐紝鍙�氳繃濡備笅鍛戒护鐩存帴鍚姩FunASR鏈嶅姟锛屽惎鍔ㄩ厤缃负涓婃涓�閿儴缃茬殑璁剧疆銆�
-
-```shell
-sudo bash funasr-runtime-deploy.sh start
-```
-
-#### 鍏抽棴FunASR鏈嶅姟
-
-```shell
-sudo bash funasr-runtime-deploy.sh stop
-```
-
-#### 閲嶅惎FunASR鏈嶅姟
-
-鏍规嵁涓婃涓�閿儴缃茬殑璁剧疆閲嶅惎鍚姩FunASR鏈嶅姟銆�
-```shell
-sudo bash funasr-runtime-deploy.sh restart
-```
-
-#### 鏇挎崲妯″瀷骞堕噸鍚疐unASR鏈嶅姟
-
-鏇挎崲姝ｅ湪浣跨敤鐨勬ā鍨嬶紝骞堕噸鏂板惎鍔‵unASR鏈嶅姟銆傛ā鍨嬮渶涓篗odelScope涓殑ASR/VAD/PUNC妯″瀷锛屾垨鑰呬粠ModelScope涓ā鍨媐inetune鍚庣殑妯″瀷銆�
-
-```shell
-sudo bash funasr-runtime-deploy.sh update model <model ID>
-
-e.g
-sudo bash funasr-runtime-deploy.sh update model damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
-```
-
-### 娴嬭瘯涓庝娇鐢ㄧ绾挎枃浠惰浆鍐欐湇鍔�
-
-鍦ㄦ湇鍔″櫒涓婂畬鎴怓unASR鏈嶅姟閮ㄧ讲浠ュ悗锛屽彲浠ラ�氳繃濡備笅鐨勬楠ゆ潵娴嬭瘯鍜屼娇鐢ㄧ绾挎枃浠惰浆鍐欐湇鍔°�傜洰鍓嶅垎鍒敮鎸丳ython銆丆++銆丣ava鐗堟湰client鐨勭殑鍛戒护琛岃繍琛岋紝浠ュ強鍙湪娴忚鍣ㄥ彲鐩存帴浣撻獙鐨刪tml缃戦〉鐗堟湰锛屾洿澶氳瑷�client鏀寔鍙傝�冩枃妗ｃ�怓unASR楂橀樁寮�鍙戞寚鍗椼�戙��
-funasr-runtime-deploy.sh杩愯缁撴潫鍚庯紝鍙�氳繃鍛戒护浠ヤ氦浜掔殑褰㈠紡鑷姩涓嬭浇娴嬭瘯鏍蜂緥samples鍒板綋鍓嶇洰褰曠殑funasr_samples涓紝骞惰缃弬鏁拌繍琛岋細
-
-```shell
-sudo bash funasr-runtime-deploy.sh client
-```
-
-鍙�夋嫨鎻愪緵鐨凱ython鍜孡inux C++鑼冧緥绋嬪簭锛屼互Python鑼冧緥涓轰緥锛�
-
-```text
-Will download sample tools for the client to show how speech recognition works.
- Please select the client you want to run.
- 1) Python
- 2) Linux_Cpp
- Enter your choice: 1
-
- Please enter the IP of server, default(127.0.0.1):
- Please enter the port of server, default(10095):
- Please enter the audio path, default(/root/funasr_samples/audio/asr_example.wav):
-
- Run pip3 install click>=8.0.4
-Looking in indexes: http://mirrors.cloud.aliyuncs.com/pypi/simple/
-Requirement already satisfied: click>=8.0.4 in /usr/local/lib/python3.8/dist-packages (8.1.3)
-
- Run pip3 install -r /root/funasr_samples/python/requirements_client.txt
-Looking in indexes: http://mirrors.cloud.aliyuncs.com/pypi/simple/
-Requirement already satisfied: websockets in /usr/local/lib/python3.8/dist-packages (from -r /root/funasr_samples/python/requirements_client.txt (line 1)) (11.0.3)
-
- Run python3 /root/funasr_samples/python/wss_client_asr.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python
-
- ...
- ...
-
- pid0_0: 娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨嬨��
-Exception: sent 1000 (OK); then received 1000 (OK)
-end
-
- If failed, you can try (python3 /root/funasr_samples/python/wss_client_asr.py --host 127.0.0.1 --port 10095 --mode offline --audio_in /root/funasr_samples/audio/asr_example.wav --send_without_sleep --output_dir ./funasr_samples/python) in your Shell.
-
-```
-
-#### python-client
-鑻ユ兂鐩存帴杩愯client杩涜娴嬭瘯锛屽彲鍙傝�冨涓嬬畝鏄撹鏄庯紝浠ython鐗堟湰涓轰緥锛�
-
-```shell
-python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --send_without_sleep --output_dir "./results"
-```
-
-鍛戒护鍙傛暟璇存槑锛�
-```text
---host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
---port 10095 閮ㄧ讲绔彛鍙�
---mode offline琛ㄧず绂荤嚎鏂囦欢杞啓
---audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
---output_dir 璇嗗埆缁撴灉淇濆瓨璺緞
-```
-
-#### cpp-client
-
-```shell
-export LD_LIBRARY_PATH=/root/funasr_samples/cpp/libs:$LD_LIBRARY_PATH
-/root/funasr_samples/cpp/funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path /root/funasr_samples/audio/asr_example.wav
-```
-
-鍛戒护鍙傛暟璇存槑锛�
-
-```text
---server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
---port 10095 閮ㄧ讲绔彛鍙�
---wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
-```
-
-### 瑙嗛demo
-
-[鐐瑰嚮姝ゅ]()
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
diff --git a/funasr/runtime/docs/SDK_tutorial_zh.md b/funasr/runtime/docs/SDK_tutorial_zh.md
new file mode 100644
index 0000000..bb4c5ed
--- /dev/null
+++ b/funasr/runtime/docs/SDK_tutorial_zh.md
@@ -0,0 +1,188 @@
+# FunASR绂荤嚎鏂囦欢杞啓鏈嶅姟渚挎嵎閮ㄧ讲鏁欑▼
+
+FunASR鎻愪緵鍙究鎹锋湰鍦版垨鑰呬簯绔湇鍔″櫒閮ㄧ讲鐨勭绾挎枃浠惰浆鍐欐湇鍔★紝鍐呮牳涓篎unASR宸插紑婧恟untime-SDK銆�
+闆嗘垚浜嗚揪鎽╅櫌璇煶瀹為獙瀹ゅ湪Modelscope绀惧尯寮�婧愮殑璇煶绔偣妫�娴�(VAD)銆丳araformer-large璇煶璇嗗埆(ASR)銆佹爣鐐规仮澶�(PUNC) 绛夌浉鍏宠兘鍔涳紝鎷ユ湁瀹屾暣鐨勮闊宠瘑鍒摼璺紝鍙互灏嗗嚑鍗佷釜灏忔椂鐨勯煶棰戞垨瑙嗛璇嗗埆鎴愬甫鏍囩偣鐨勬枃瀛楋紝鑰屼笖鏀寔涓婄櫨璺姹傚悓鏃惰繘琛岃浆鍐欍��
+
+## 鏈嶅姟鍣ㄩ厤缃�
+
+鐢ㄦ埛鍙互鏍规嵁鑷繁鐨勪笟鍔￠渶姹傦紝閫夋嫨鍚堥�傜殑鏈嶅姟鍣ㄩ厤缃紝鎺ㄨ崘閰嶇疆涓猴細
+- 閰嶇疆1: 锛圶86锛岃绠楀瀷锛夛紝4鏍竩CPU锛屽唴瀛�8G锛屽崟鏈哄彲浠ユ敮鎸佸ぇ绾�32璺殑璇锋眰
+- 閰嶇疆2: 锛圶86锛岃绠楀瀷锛夛紝16鏍竩CPU锛屽唴瀛�32G锛屽崟鏈哄彲浠ユ敮鎸佸ぇ绾�64璺殑璇锋眰
+- 閰嶇疆3: 锛圶86锛岃绠楀瀷锛夛紝64鏍竩CPU锛屽唴瀛�128G锛屽崟鏈哄彲浠ユ敮鎸佸ぇ绾�200璺殑璇锋眰
+
+浜戞湇鍔″巶鍟嗭紝閽堝鏂扮敤鎴凤紝鏈�3涓湀鍏嶈垂璇曠敤娲诲姩锛岀敵璇锋暀绋嬶紙[鐐瑰嚮姝ゅ](./aliyun_server_tutorial.md)锛�
+
+## 蹇�熶笂鎵�
+
+### 鏈嶅姟绔惎鍔�
+
+涓嬭浇閮ㄧ讲宸ュ叿`funasr-runtime-deploy-offline-cpu-zh.sh`
+
+```shell
+curl -O https://raw.githubusercontent.com/alibaba-damo-academy/FunASR/main/funasr/runtime/deploy_tools/funasr-runtime-deploy-offline-cpu-zh.sh;
+# 濡傞亣鍒扮綉缁滈棶棰橈紝涓浗澶ч檰鐢ㄦ埛锛屽彲浠ョ敤涓笅闈㈢殑鍛戒护锛�
+# curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh;
+```
+
+鎵ц閮ㄧ讲宸ュ叿锛屽湪鎻愮ず澶勮緭鍏ュ洖杞﹂敭鍗冲彲瀹屾垚鏈嶅姟绔畨瑁呬笌閮ㄧ讲銆傜洰鍓嶄究鎹烽儴缃插伐鍏锋殏鏃朵粎鏀寔Linux鐜锛屽叾浠栫幆澧冮儴缃插弬鑰冨紑鍙戞寚鍗楋紙[鐐瑰嚮姝ゅ](./SDK_advanced_guide_zh.md)锛�
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh install --workspace /root/funasr-runtime-resources
+```
+
+### 瀹㈡埛绔祴璇曚笌浣跨敤
+
+杩愯涓婇潰瀹夎鎸囦护鍚庯紝浼氬湪/root/funasr-runtime-resources锛堥粯璁ゅ畨瑁呯洰褰曪級涓笅杞藉鎴风娴嬭瘯宸ュ叿鐩綍samples锛�
+鎴戜滑浠ython璇█瀹㈡埛绔负渚嬶紝杩涜璇存槑锛屾敮鎸佸绉嶉煶棰戞牸寮忚緭鍏ワ紙.wav, .pcm, .mp3绛夛級锛屼篃鏀寔瑙嗛杈撳叆(.mp4绛�)锛屼互鍙婂鏂囦欢鍒楄〃wav.scp杈撳叆锛屽叾浠栫増鏈鎴风璇峰弬鑰冩枃妗ｏ紙[鐐瑰嚮姝ゅ](#瀹㈡埛绔敤娉曡瑙�)锛�
+
+```shell
+python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+```
+
+## 瀹㈡埛绔敤娉曡瑙�
+
+鍦ㄦ湇鍔″櫒涓婂畬鎴怓unASR鏈嶅姟閮ㄧ讲浠ュ悗锛屽彲浠ラ�氳繃濡備笅鐨勬楠ゆ潵娴嬭瘯鍜屼娇鐢ㄧ绾挎枃浠惰浆鍐欐湇鍔°��
+鐩墠鍒嗗埆鏀寔浠ヤ笅鍑犵缂栫▼璇█瀹㈡埛绔�
+
+- [Python](#python-client)
+- [CPP](#cpp-client)
+- [html缃戦〉鐗堟湰](#Html缃戦〉鐗�)
+- [Java](#Java-client)
+
+鏇村鐗堟湰瀹㈡埛绔敮鎸佽鍙傝�僛寮�鍙戞寚鍗梋(./SDK_advanced_guide_offline_zh.md)
+
+### python-client
+鑻ユ兂鐩存帴杩愯client杩涜娴嬭瘯锛屽彲鍙傝�冨涓嬬畝鏄撹鏄庯紝浠ython鐗堟湰涓轰緥锛�
+
+```shell
+python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav" --output_dir "./results"
+```
+
+鍛戒护鍙傛暟璇存槑锛�
+```text
+--host 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--port 10095 閮ㄧ讲绔彛鍙�
+--mode offline琛ㄧず绂荤嚎鏂囦欢杞啓
+--audio_in 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰勶紝鏂囦欢鍒楄〃wav.scp
+--output_dir 璇嗗埆缁撴灉淇濆瓨璺緞
+```
+
+### cpp-client
+杩涘叆samples/cpp鐩綍鍚庯紝鍙互鐢╟pp杩涜娴嬭瘯锛屾寚浠ゅ涓嬶細
+```shell
+./funasr-wss-client --server-ip 127.0.0.1 --port 10095 --wav-path ../audio/asr_example.wav
+```
+
+鍛戒护鍙傛暟璇存槑锛�
+
+```text
+--server-ip 涓篎unASR runtime-SDK鏈嶅姟閮ㄧ讲鏈哄櫒ip锛岄粯璁や负鏈満ip锛�127.0.0.1锛夛紝濡傛灉client涓庢湇鍔′笉鍦ㄥ悓涓�鍙版湇鍔″櫒锛岄渶瑕佹敼涓洪儴缃叉満鍣╥p
+--port 10095 閮ㄧ讲绔彛鍙�
+--wav-path 闇�瑕佽繘琛岃浆鍐欑殑闊抽鏂囦欢锛屾敮鎸佹枃浠惰矾寰�
+```
+
+### Html缃戦〉鐗�
+
+鍦ㄦ祻瑙堝櫒涓墦寮� html/static/index.html锛屽嵆鍙嚭鐜板涓嬮〉闈紝鏀寔楹﹀厠椋庤緭鍏ヤ笌鏂囦欢涓婁紶锛岀洿鎺ヨ繘琛屼綋楠�
+
+<img src="images/html.png" width="900"/>
+
+### Java-client
+
+```shell
+FunasrWsClient --host localhost --port 10095 --audio_in ./asr_example.wav --mode offline
+```
+璇︾粏鍙互鍙傝�冩枃妗ｏ紙[鐐瑰嚮姝ゅ](../java/readme.md)锛�
+
+## 鏈嶅姟绔敤娉曡瑙�
+
+### 鍚姩宸茬粡閮ㄧ讲杩囩殑FunASR鏈嶅姟
+涓�閿儴缃插悗鑻ュ嚭鐜伴噸鍚數鑴戠瓑鍏抽棴Docker鐨勫姩浣滐紝鍙�氳繃濡備笅鍛戒护鐩存帴鍚姩FunASR鏈嶅姟锛屽惎鍔ㄩ厤缃负涓婃涓�閿儴缃茬殑璁剧疆銆�
+
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh start
+```
+
+### 鍏抽棴FunASR鏈嶅姟
+
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh stop
+```
+
+### 閲嶅惎FunASR鏈嶅姟
+
+鏍规嵁涓婃涓�閿儴缃茬殑璁剧疆閲嶅惎鍚姩FunASR鏈嶅姟銆�
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh restart
+```
+
+### 鏇挎崲妯″瀷骞堕噸鍚疐unASR鏈嶅姟
+
+鏇挎崲姝ｅ湪浣跨敤鐨勬ā鍨嬶紝骞堕噸鏂板惎鍔‵unASR鏈嶅姟銆傛ā鍨嬮渶涓篗odelScope涓殑ASR/VAD/PUNC妯″瀷锛屾垨鑰呬粠ModelScope涓ā鍨媐inetune鍚庣殑妯″瀷銆�
+
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--asr_model | --vad_model | --punc_model] <model_id or local model path>
+
+e.g
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update --asr_model damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
+```
+
+### 鏇存柊鍙傛暟骞堕噸鍚疐unASR鏈嶅姟
+
+鏇存柊宸查厤缃弬鏁帮紝骞堕噸鏂板惎鍔‵unASR鏈嶅姟鐢熸晥銆傚彲鏇存柊鍙傛暟鍖呮嫭瀹夸富鏈哄拰Docker鐨勭鍙ｅ彿锛屼互鍙婃帹鐞嗗拰IO鐨勭嚎绋嬫暟閲忋��
+
+```shell
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--host_port | --docker_port] <port number>
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--decode_thread_num | --io_thread_num] <the number of threads>
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update [--workspace] <workspace in local>
+
+e.g
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update --decode_thread_num 32
+sudo bash funasr-runtime-deploy-offline-cpu-zh.sh update --workspace /root/funasr-runtime-resources
+```
+
+
+## 鏈嶅姟绔惎鍔ㄨ繃绋嬮厤缃瑙�
+
+##### 閫夋嫨FunASR Docker闀滃儚
+鎺ㄨ崘閫夋嫨1)浣跨敤鎴戜滑鐨勬渶鏂板彂甯冪増闀滃儚锛屼篃鍙�夋嫨鍘嗗彶鐗堟湰銆�
+```text
+[1/5]
+ Getting the list of docker images, please wait a few seconds.
+ [DONE]
+
+ Please choose the Docker image.
+ 1) registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0
+ Enter your choice, default(1):
+ You have chosen the Docker image: registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0
+```
+
+
+##### 璁剧疆瀹夸富鏈烘彁渚涚粰FunASR鐨勭鍙�
+璁剧疆鎻愪緵缁橠ocker鐨勫涓绘満绔彛锛岄粯璁や负10095銆傝淇濊瘉姝ょ鍙ｅ彲鐢ㄣ��
+```text
+[2/5]
+ Please input the opened port in the host used for FunASR server.
+ Setting the opened host port [1-65535], default(10095):
+ The port of the host is 10095
+ The port in Docker for FunASR server is 10095
+```
+
+
+## 瑙嗛demo
+
+[鐐瑰嚮姝ゅ]()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/funasr/runtime/docs/aliyun_server_tutorial.md b/funasr/runtime/docs/aliyun_server_tutorial.md
index e68d8bf..5cd47c2 100644
--- a/funasr/runtime/docs/aliyun_server_tutorial.md
+++ b/funasr/runtime/docs/aliyun_server_tutorial.md
@@ -2,16 +2,6 @@
鎴戜滑浠ラ樋閲屼簯锛圼鐐规閾炬帴](https://www.aliyun.com/)锛変负渚嬶紝婕旂ず濡備綍鐢宠浜戞湇鍔″櫒
-## 鏈嶅姟鍣ㄩ厤缃�
-
-鐢ㄦ埛鍙互鏍规嵁鑷繁鐨勪笟鍔￠渶姹傦紝閫夋嫨鍚堥�傜殑鏈嶅姟鍣ㄩ厤缃紝鎺ㄨ崘閰嶇疆涓猴細
-- 閰嶇疆涓�锛堥珮閰嶏級锛歑86鏋舵瀯锛�32/64鏍�8369CPU锛屽唴瀛�8G浠ヤ笂锛�
-- 閰嶇疆浜岋細X86鏋舵瀯锛�32/64鏍�8163CPU锛屽唴瀛�8G浠ヤ笂锛�
-
-璇︾粏鎬ц兘娴嬭瘯鎶ュ憡锛歔鐐规閾炬帴](./benchmark_onnx_cpp.md)
-
-鎴戜滑浠ュ厤璐硅瘯鐢紙1锝�3涓湀锛変负渚嬶紝婕旂ず濡備綍鐢宠鏈嶅姟鍣ㄦ祦绋嬶紝鍥炬枃姝ラ濡備笅锛�
-
### 鐧婚檰涓汉璐﹀彿
鎵撳紑闃块噷浜戝畼缃慬鐐规閾炬帴](https://www.aliyun.com/)锛屾敞鍐屽苟鐧婚檰涓汉璐﹀彿锛屽涓嬪浘鏍囧彿1鎵�绀�
@@ -69,6 +59,6 @@
<img src="images/aliyun12.png" width="900"/>
-涓婂浘琛ㄧず宸茬粡鎴愬姛鐢宠浜嗕簯鏈嶅姟鍣紝鍚庣画鍙互鏍规嵁FunASR runtime-SDK閮ㄧ讲鏂囨。杩涜涓�閿儴缃诧紙[鐐瑰嚮姝ゅ]()锛�
+涓婂浘琛ㄧず宸茬粡鎴愬姛鐢宠浜嗕簯鏈嶅姟鍣紝鍚庣画鍙互鏍规嵁FunASR runtime-SDK閮ㄧ讲鏂囨。杩涜涓�閿儴缃诧紙[鐐瑰嚮姝ゅ](./SDK_tutorial_cn.md)锛�
diff --git a/funasr/runtime/docs/docker_offline_cpu_zh_lists b/funasr/runtime/docs/docker_offline_cpu_zh_lists
new file mode 100644
index 0000000..6742f73
--- /dev/null
+++ b/funasr/runtime/docs/docker_offline_cpu_zh_lists
@@ -0,0 +1,8 @@
+DOCKER:
+ funasr-runtime-sdk-cpu-0.1.0
+DEFAULT_ASR_MODEL:
+ damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx
+DEFAULT_VAD_MODEL:
+ damo/speech_fsmn_vad_zh-cn-16k-common-onnx
+DEFAULT_PUNC_MODEL:
+ damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx
diff --git a/funasr/runtime/docs/images/html.png b/funasr/runtime/docs/images/html.png
new file mode 100644
index 0000000..e0c86ba
--- /dev/null
+++ b/funasr/runtime/docs/images/html.png
Binary files differ
diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
index fcdc83c..ed44795 100644
--- a/funasr/runtime/python/websocket/README.md
+++ b/funasr/runtime/python/websocket/README.md
@@ -74,7 +74,7 @@
Loadding from wav.scp(kaldi style)
```shell
# --chunk_interval, "10": 600/10=60ms, "5"=600/5=120ms, "20": 600/12=30ms
-python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --send_without_sleep --output_dir "./results"
+python wss_client_asr.py --host "0.0.0.0" --port 10095 --mode offline --chunk_interval 10 --words_max_print 100 --audio_in "./data/wav.scp" --output_dir "./results"
```
##### ASR streaming client
diff --git a/funasr/runtime/python/websocket/wss_client_asr.py b/funasr/runtime/python/websocket/wss_client_asr.py
index 2ea8a16..45b8ac4 100644
--- a/funasr/runtime/python/websocket/wss_client_asr.py
+++ b/funasr/runtime/python/websocket/wss_client_asr.py
@@ -40,7 +40,7 @@
help="audio_in")
parser.add_argument("--send_without_sleep",
action="store_true",
- default=False,
+ default=True,
help="if audio_in is set, send_without_sleep")
parser.add_argument("--test_thread_num",
type=int,
@@ -161,7 +161,8 @@
#voices.put(message)
await websocket.send(message)
- sleep_duration = 0.001 if args.send_without_sleep else 60 * args.chunk_size[1] / args.chunk_interval / 1000
+ sleep_duration = 0.001 if args.mode == "offline" else 60 * args.chunk_size[1] / args.chunk_interval / 1000
+
await asyncio.sleep(sleep_duration)
# when all data sent, we need to close websocket
while not voices.empty():
diff --git a/funasr/runtime/readme.md b/funasr/runtime/readme.md
index 93a1547..1a535e1 100644
--- a/funasr/runtime/readme.md
+++ b/funasr/runtime/readme.md
@@ -27,4 +27,4 @@
### Advanced Development Guide
-The documentation mainly targets advanced developers who require modifications and customization of the service. It supports downloading model deployments from modelscope and also supports deploying models that users have fine-tuned. For detailed information, please refer to the documentation available by [docs](websocket/readme.md)
+The documentation mainly targets advanced developers who require modifications and customization of the service. It supports downloading model deployments from modelscope and also supports deploying models that users have fine-tuned. For detailed information, please refer to the documentation available by [docs](./docs/SDK_advanced_guide_offline.md)
diff --git a/funasr/runtime/readme_cn.md b/funasr/runtime/readme_cn.md
index 3a76c08..492b97c 100644
--- a/funasr/runtime/readme_cn.md
+++ b/funasr/runtime/readme_cn.md
@@ -9,23 +9,23 @@
- 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟锛圙PU鐗堟湰锛夛紝杩涜涓�
- 鑻辨枃绂荤嚎杞啓鏈嶅姟锛岃繘琛屼腑
- 娴佸紡璇煶璇嗗埆鏈嶅姟锛岃繘琛屼腑
-- 銆傘�傘��
+- 鏇村鏀寔涓�
## 涓枃绂荤嚎鏂囦欢杞啓鏈嶅姟閮ㄧ讲锛圕PU鐗堟湰锛�
-鐩墠FunASR runtime-SDK-0.0.1鐗堟湰宸叉敮鎸佷腑鏂囪闊崇绾挎枃浠舵湇鍔￠儴缃诧紙CPU鐗堟湰锛夛紝鎷ユ湁瀹屾暣鐨勮闊宠瘑鍒摼璺紝鍙互灏嗗嚑鍗佷釜灏忔椂鐨勯煶棰戣瘑鍒垚甯︽爣鐐圭殑鏂囧瓧锛岃�屼笖鏀寔涓婄櫨璺苟鍙戝悓鏃惰繘琛岃瘑鍒��
+涓枃璇煶绂荤嚎鏂囦欢鏈嶅姟閮ㄧ讲锛圕PU鐗堟湰锛夛紝鎷ユ湁瀹屾暣鐨勮闊宠瘑鍒摼璺紝鍙互灏嗗嚑鍗佷釜灏忔椂鐨勯煶棰戜笌瑙嗛璇嗗埆鎴愬甫鏍囩偣鐨勬枃瀛楋紝鑰屼笖鏀寔涓婄櫨璺姹傚悓鏃惰繘琛岃浆鍐欍��
+涓轰簡鏀寔涓嶅悓鐢ㄦ埛鐨勯渶姹傦紝閽堝涓嶅悓鍦烘櫙锛屽噯澶囦簡涓嶅悓鐨勫浘鏂囨暀绋嬶細
-涓轰簡鏀寔涓嶅悓鐢ㄦ埛鐨勯渶姹傦紝鎴戜滑鍒嗗埆閽堝灏忕櫧涓庨珮闃跺紑鍙戣�咃紝鍑嗗浜嗕笉鍚岀殑鍥炬枃鏁欑▼锛�
+### 渚挎嵎閮ㄧ讲鏁欑▼
+
+閫傜敤鍦烘櫙涓猴紝瀵规湇鍔￠儴缃睸DK鏃犱慨鏀归渶姹傦紝閮ㄧ讲妯″瀷鏉ヨ嚜浜嶮odelScope锛屾垨鑰呯敤鎴穎inetune锛岃缁嗘暀绋嬪弬鑰冿紙[鐐瑰嚮姝ゅ](./docs/SDK_tutorial_zh.md)锛�
+
+
+### 寮�鍙戞寚鍗�
+
+閫傜敤鍦烘櫙涓猴紝瀵规湇鍔￠儴缃睸DK鏈変慨鏀归渶姹傦紝閮ㄧ讲妯″瀷鏉ヨ嚜浜嶮odelScope锛屾垨鑰呯敤鎴穎inetune锛岃缁嗘枃妗ｅ弬鑰冿紙[鐐瑰嚮姝ゅ](./docs/SDK_advanced_guide_offline_zh.md)锛�
### 鎶�鏈師鐞嗘彮绉�
鏂囨。浠嬬粛浜嗚儗鍚庢妧鏈師鐞嗭紝璇嗗埆鍑嗙‘鐜囷紝璁＄畻鏁堢巼绛夛紝浠ュ強鏍稿績浼樺娍浠嬬粛锛氫究鎹枫�侀珮绮惧害銆侀珮鏁堢巼銆侀暱闊抽閾捐矾锛岃缁嗘枃妗ｅ弬鑰冿紙[鐐瑰嚮姝ゅ](https://mp.weixin.qq.com/s?__biz=MzA3MTQ0NTUyMw==&tempkey=MTIyNF84d05USjMxSEpPdk5GZXBJUFNJNzY0bU1DTkxhV19mcWY4MTNWQTJSYXhUaFgxOWFHZTZKR0JzWC1JRmRCdUxCX2NoQXg0TzFpNmVJX2R1WjdrcC02N2FEcUc3MDhzVVhpNWQ5clU4QUdqNFdkdjFYb18xRjlZMmc5c3RDOTl0U0NiRkJLb05ZZ0RmRlVkVjFCZnpXNWFBVlRhbXVtdWs4bUMwSHZnfn4%3D&chksm=1f2c3254285bbb42bc8f76a82e9c5211518a0bb1ff8c357d085c1b78f675ef2311f3be6e282c#rd)锛�
-
-### 渚挎嵎閮ㄧ讲鏁欑▼
-
-鏂囨。涓昏閽堝灏忕櫧鐢ㄦ埛涓庡垵绾у紑鍙戣�咃紝娌℃湁淇敼銆佸畾鍒堕渶姹傦紝鏀寔浠巑odelscope涓笅杞芥ā鍨嬮儴缃诧紝涔熸敮鎸佺敤鎴穎inetune鍚庣殑妯″瀷閮ㄧ讲锛岃缁嗘暀绋嬪弬鑰冿紙[鐐瑰嚮姝ゅ](./docs/SDK_tutorial_cn.md)锛�
-
-### 楂橀樁寮�鍙戞寚鍗�
-
-鏂囨。涓昏閽堝楂橀樁寮�鍙戣�咃紝闇�瑕佸鏈嶅姟杩涜淇敼涓庡畾鍒讹紝鏀寔浠巑odelscope涓笅杞芥ā鍨嬮儴缃诧紝涔熸敮鎸佺敤鎴穎inetune鍚庣殑妯″瀷閮ㄧ讲锛岃缁嗘枃妗ｅ弬鑰冿紙[鐐瑰嚮姝ゅ](./docs/SDK_advanced_guide_cn.md)锛�
diff --git a/funasr/runtime/run_server.sh b/funasr/runtime/run_server.sh
new file mode 100755
index 0000000..2ab6491
--- /dev/null
+++ b/funasr/runtime/run_server.sh
@@ -0,0 +1,25 @@
+
+download_model_dir="/workspace/models"
+model_dir="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx"
+vad_dir="damo/speech_fsmn_vad_zh-cn-16k-common-onnx"
+punc_dir="damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx"
+decoder_thread_num=32
+io_thread_num=8
+port=10095
+certfile="../../../ssl_key/server.crt"
+keyfile="../../../ssl_key/server.key"
+
+. ../../egs/aishell/transformer/utils/parse_options.sh || exit 1;
+
+cd /workspace/FunASR/funasr/runtime/websocket/build/bin
+./funasr-wss-server \
+ --download-model-dir ${download_model_dir} \
+ --model-dir ${model_dir} \
+ --vad-dir ${vad_dir} \
+ --punc-dir ${punc_dir} \
+ --decoder-thread-num ${decoder_thread_num} \
+ --io-thread-num ${io_thread_num} \
+ --port ${port} \
+ --certfile ${certfile} \
+ --keyfile ${keyfile}
+
diff --git a/funasr/tasks/asr.py b/funasr/tasks/asr.py
index 3ab68df..a6f7eac 100644
--- a/funasr/tasks/asr.py
+++ b/funasr/tasks/asr.py
@@ -47,6 +47,7 @@
from funasr.models.e2e_sa_asr import SAASRModel
from funasr.models.e2e_uni_asr import UniASR
from funasr.models.e2e_asr_transducer import TransducerModel, UnifiedTransducerModel
+from funasr.models.e2e_asr_bat import BATModel
from funasr.models.encoder.abs_encoder import AbsEncoder
from funasr.models.encoder.conformer_encoder import ConformerEncoder, ConformerChunkEncoder
from funasr.models.encoder.data2vec_encoder import Data2VecEncoder
@@ -66,7 +67,7 @@
from funasr.models.postencoder.hugging_face_transformers_postencoder import (
HuggingFaceTransformersPostEncoder, # noqa: H301
)
-from funasr.models.predictor.cif import CifPredictor, CifPredictorV2, CifPredictorV3
+from funasr.models.predictor.cif import CifPredictor, CifPredictorV2, CifPredictorV3, BATPredictor
from funasr.models.preencoder.abs_preencoder import AbsPreEncoder
from funasr.models.preencoder.linear import LinearProjection
from funasr.models.preencoder.sinc import LightweightSincConvs
@@ -135,6 +136,7 @@
timestamp_prediction=TimestampPredictor,
rnnt=TransducerModel,
rnnt_unified=UnifiedTransducerModel,
+ bat=BATModel,
sa_asr=SAASRModel,
),
type_check=FunASRModel,
@@ -266,6 +268,7 @@
ctc_predictor=None,
cif_predictor_v2=CifPredictorV2,
cif_predictor_v3=CifPredictorV3,
+ bat_predictor=BATPredictor,
),
type_check=None,
default="cif_predictor",
@@ -1508,6 +1511,139 @@
return model
+class ASRBATTask(ASRTask):
+ """ASR Boundary Aware Transducer Task definition."""
+
+ num_optimizers: int = 1
+
+ class_choices_list = [
+ model_choices,
+ frontend_choices,
+ specaug_choices,
+ normalize_choices,
+ encoder_choices,
+ rnnt_decoder_choices,
+ joint_network_choices,
+ predictor_choices,
+ ]
+
+ trainer = Trainer
+
+ @classmethod
+ def build_model(cls, args: argparse.Namespace) -> BATModel:
+ """Required data depending on task mode.
+ Args:
+ cls: ASRBATTask object.
+ args: Task arguments.
+ Return:
+ model: ASR BAT model.
+ """
+ assert check_argument_types()
+
+ if isinstance(args.token_list, str):
+ with open(args.token_list, encoding="utf-8") as f:
+ token_list = [line.rstrip() for line in f]
+
+ # Overwriting token_list to keep it as "portable".
+ args.token_list = list(token_list)
+ elif isinstance(args.token_list, (tuple, list)):
+ token_list = list(args.token_list)
+ else:
+ raise RuntimeError("token_list must be str or list")
+ vocab_size = len(token_list)
+ logging.info(f"Vocabulary size: {vocab_size }")
+
+ # 1. frontend
+ if args.input_size is None:
+ # Extract features in the model
+ frontend_class = frontend_choices.get_class(args.frontend)
+ frontend = frontend_class(**args.frontend_conf)
+ input_size = frontend.output_size()
+ else:
+ # Give features from data-loader
+ frontend = None
+ input_size = args.input_size
+
+ # 2. Data augmentation for spectrogram
+ if args.specaug is not None:
+ specaug_class = specaug_choices.get_class(args.specaug)
+ specaug = specaug_class(**args.specaug_conf)
+ else:
+ specaug = None
+
+ # 3. Normalization layer
+ if args.normalize is not None:
+ normalize_class = normalize_choices.get_class(args.normalize)
+ normalize = normalize_class(**args.normalize_conf)
+ else:
+ normalize = None
+
+ # 4. Encoder
+ if getattr(args, "encoder", None) is not None:
+ encoder_class = encoder_choices.get_class(args.encoder)
+ encoder = encoder_class(input_size, **args.encoder_conf)
+ else:
+ encoder = Encoder(input_size, **args.encoder_conf)
+ encoder_output_size = encoder.output_size()
+
+ # 5. Decoder
+ rnnt_decoder_class = rnnt_decoder_choices.get_class(args.rnnt_decoder)
+ decoder = rnnt_decoder_class(
+ vocab_size,
+ **args.rnnt_decoder_conf,
+ )
+ decoder_output_size = decoder.output_size
+
+ if getattr(args, "decoder", None) is not None:
+ att_decoder_class = decoder_choices.get_class(args.decoder)
+
+ att_decoder = att_decoder_class(
+ vocab_size=vocab_size,
+ encoder_output_size=encoder_output_size,
+ **args.decoder_conf,
+ )
+ else:
+ att_decoder = None
+ # 6. Joint Network
+ joint_network = JointNetwork(
+ vocab_size,
+ encoder_output_size,
+ decoder_output_size,
+ **args.joint_network_conf,
+ )
+
+ predictor_class = predictor_choices.get_class(args.predictor)
+ predictor = predictor_class(**args.predictor_conf)
+
+ # 7. Build model
+ try:
+ model_class = model_choices.get_class(args.model)
+ except AttributeError:
+ model_class = model_choices.get_class("rnnt_unified")
+
+ model = model_class(
+ vocab_size=vocab_size,
+ token_list=token_list,
+ frontend=frontend,
+ specaug=specaug,
+ normalize=normalize,
+ encoder=encoder,
+ decoder=decoder,
+ att_decoder=att_decoder,
+ joint_network=joint_network,
+ predictor=predictor,
+ **args.model_conf,
+ )
+ # 8. Initialize model
+ if args.init is not None:
+ raise NotImplementedError(
+ "Currently not supported.",
+ "Initialization part will be reworked in a short future.",
+ )
+
+ #assert check_return_type(model)
+
+ return model
class ASRTaskSAASR(ASRTask):
# If you need more than one optimizers, change this value
--
Gitblit v1.9.1