From 28a19dbc4e85d3b8a4ec2ef7483bba64d422b43f Mon Sep 17 00:00:00 2001
From: aky15 <ankeyu.aky@11.17.44.249>
Date: 星期三, 12 四月 2023 18:03:06 +0800
Subject: [PATCH] Merge remote-tracking branch 'origin/main' into dev_aky
---
funasr/bin/asr_inference_paraformer.py | 734 +++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 542 insertions(+), 192 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
old mode 100755
new mode 100644
index 9dcd0b8..8cbd419
--- a/funasr/bin/asr_inference_paraformer.py
+++ b/funasr/bin/asr_inference_paraformer.py
@@ -3,6 +3,11 @@
import logging
import sys
import time
+import copy
+import os
+import codecs
+import tempfile
+import requests
from pathlib import Path
from typing import Optional
from typing import Sequence
@@ -35,26 +40,18 @@
from funasr.utils.types import str_or_none
from funasr.utils import asr_utils, wav_utils, postprocess_utils
from funasr.models.frontend.wav_frontend import WavFrontend
+from funasr.models.e2e_asr_paraformer import BiCifParaformer, ContextualParaformer
+from funasr.export.models.e2e_asr_paraformer import Paraformer as Paraformer_export
+from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
+from funasr.bin.tp_inference import SpeechText2Timestamp
-from modelscope.utils.logger import get_logger
-
-logger = get_logger()
-
-header_colors = '\033[95m'
-end_colors = '\033[0m'
-
-global_asr_language: str = 'zh-cn'
-global_sample_rate: Union[int, Dict[Any, int]] = {
- 'audio_fs': 16000,
- 'model_fs': 16000
-}
class Speech2Text:
"""Speech2Text class
Examples:
>>> import soundfile
- >>> speech2text = Speech2Text("asr_config.yml", "asr.pth")
+ >>> speech2text = Speech2Text("asr_config.yml", "asr.pb")
>>> audio, rate = soundfile.read("speech.wav")
>>> speech2text(audio)
[(text, token, token_int, hypothesis object), ...]
@@ -65,6 +62,7 @@
self,
asr_train_config: Union[Path, str] = None,
asr_model_file: Union[Path, str] = None,
+ cmvn_file: Union[Path, str] = None,
lm_train_config: Union[Path, str] = None,
lm_file: Union[Path, str] = None,
token_type: str = None,
@@ -80,6 +78,7 @@
penalty: float = 0.0,
nbest: int = 1,
frontend_conf: dict = None,
+ hotword_list_or_file: str = None,
**kwargs,
):
assert check_argument_types()
@@ -87,19 +86,23 @@
# 1. Build ASR model
scorers = {}
asr_model, asr_train_args = ASRTask.build_model_from_file(
- asr_train_config, asr_model_file, device
+ asr_train_config, asr_model_file, cmvn_file, device
)
- if asr_model.frontend is None and frontend_conf is not None:
- frontend = WavFrontend(**frontend_conf)
- asr_model.frontend = frontend
+ frontend = None
+ if asr_train_args.frontend is not None and asr_train_args.frontend_conf is not None:
+ frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf)
+
logging.info("asr_model: {}".format(asr_model))
logging.info("asr_train_args: {}".format(asr_train_args))
asr_model.to(dtype=getattr(torch, dtype)).eval()
- ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
+ if asr_model.ctc != None:
+ ctc = CTCPrefixScorer(ctc=asr_model.ctc, eos=asr_model.eos)
+ scorers.update(
+ ctc=ctc
+ )
token_list = asr_model.token_list
scorers.update(
- ctc=ctc,
length_bonus=LengthBonus(len(token_list)),
)
@@ -141,7 +144,7 @@
for scorer in scorers.values():
if isinstance(scorer, torch.nn.Module):
scorer.to(device=device, dtype=getattr(torch, dtype)).eval()
- logging.info(f"Beam_search: {beam_search}")
+
logging.info(f"Decoding device={device}, dtype={dtype}")
# 5. [Optional] Build Text converter: e.g. bpe-sym -> Text
@@ -166,17 +169,272 @@
self.asr_train_args = asr_train_args
self.converter = converter
self.tokenizer = tokenizer
- has_lm = lm_weight == 0.0 or lm_file is None
- if ctc_weight == 0.0 and has_lm:
+
+ # 6. [Optional] Build hotword list from str, local file or url
+ self.hotword_list = None
+ self.hotword_list = self.generate_hotwords_list(hotword_list_or_file)
+
+ is_use_lm = lm_weight != 0.0 and lm_file is not None
+ if (ctc_weight == 0.0 or asr_model.ctc == None) and not is_use_lm:
beam_search = None
self.beam_search = beam_search
+ logging.info(f"Beam_search: {self.beam_search}")
self.beam_search_transducer = beam_search_transducer
self.maxlenratio = maxlenratio
self.minlenratio = minlenratio
self.device = device
self.dtype = dtype
self.nbest = nbest
+ self.frontend = frontend
+ self.encoder_downsampling_factor = 1
+ if asr_train_args.encoder == "data2vec_encoder" or asr_train_args.encoder_conf["input_layer"] == "conv2d":
+ self.encoder_downsampling_factor = 4
+ @torch.no_grad()
+ def __call__(
+ self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None,
+ begin_time: int = 0, end_time: int = None,
+ ):
+ """Inference
+
+ Args:
+ speech: Input speech data
+ Returns:
+ text, token, token_int, hyp
+
+ """
+ assert check_argument_types()
+
+ # Input as audio signal
+ if isinstance(speech, np.ndarray):
+ speech = torch.tensor(speech)
+
+ if self.frontend is not None:
+ feats, feats_len = self.frontend.forward(speech, speech_lengths)
+ feats = to_device(feats, device=self.device)
+ feats_len = feats_len.int()
+ self.asr_model.frontend = None
+ else:
+ feats = speech
+ feats_len = speech_lengths
+ lfr_factor = max(1, (feats.size()[-1] // 80) - 1)
+ batch = {"speech": feats, "speech_lengths": feats_len}
+
+ # a. To device
+ batch = to_device(batch, device=self.device)
+
+ # b. Forward Encoder
+ enc, enc_len = self.asr_model.encode(**batch)
+ if isinstance(enc, tuple):
+ enc = enc[0]
+ # assert len(enc) == 1, len(enc)
+ enc_len_batch_total = torch.sum(enc_len).item() * self.encoder_downsampling_factor
+
+ predictor_outs = self.asr_model.calc_predictor(enc, enc_len)
+ pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index = predictor_outs[0], predictor_outs[1], \
+ predictor_outs[2], predictor_outs[3]
+ pre_token_length = pre_token_length.round().long()
+ if torch.max(pre_token_length) < 1:
+ return []
+ if not isinstance(self.asr_model, ContextualParaformer):
+ if self.hotword_list:
+ logging.warning("Hotword is given but asr model is not a ContextualParaformer.")
+ decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
+ decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
+ else:
+ decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length, hw_list=self.hotword_list)
+ decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
+
+ if isinstance(self.asr_model, BiCifParaformer):
+ _, _, us_alphas, us_peaks = self.asr_model.calc_predictor_timestamp(enc, enc_len,
+ pre_token_length) # test no bias cif2
+
+ results = []
+ b, n, d = decoder_out.size()
+ for i in range(b):
+ x = enc[i, :enc_len[i], :]
+ am_scores = decoder_out[i, :pre_token_length[i], :]
+ if self.beam_search is not None:
+ nbest_hyps = self.beam_search(
+ x=x, am_scores=am_scores, maxlenratio=self.maxlenratio, minlenratio=self.minlenratio
+ )
+
+ nbest_hyps = nbest_hyps[: self.nbest]
+ else:
+ yseq = am_scores.argmax(dim=-1)
+ score = am_scores.max(dim=-1)[0]
+ score = torch.sum(score, dim=-1)
+ # pad with mask tokens to ensure compatibility with sos/eos tokens
+ yseq = torch.tensor(
+ [self.asr_model.sos] + yseq.tolist() + [self.asr_model.eos], device=yseq.device
+ )
+ nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
+
+ for hyp in nbest_hyps:
+ assert isinstance(hyp, (Hypothesis)), type(hyp)
+
+ # remove sos/eos and get results
+ last_pos = -1
+ if isinstance(hyp.yseq, list):
+ token_int = hyp.yseq[1:last_pos]
+ else:
+ token_int = hyp.yseq[1:last_pos].tolist()
+
+ # remove blank symbol id, which is assumed to be 0
+ token_int = list(filter(lambda x: x != 0 and x != 2, token_int))
+
+ # Change integer-ids to tokens
+ token = self.converter.ids2tokens(token_int)
+
+ if self.tokenizer is not None:
+ text = self.tokenizer.tokens2text(token)
+ else:
+ text = None
+
+ if isinstance(self.asr_model, BiCifParaformer):
+ _, timestamp = ts_prediction_lfr6_standard(us_alphas[i],
+ us_peaks[i],
+ copy.copy(token),
+ vad_offset=begin_time)
+ results.append((text, token, token_int, hyp, timestamp, enc_len_batch_total, lfr_factor))
+ else:
+ results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
+
+ # assert check_return_type(results)
+ return results
+
+ def generate_hotwords_list(self, hotword_list_or_file):
+ # for None
+ if hotword_list_or_file is None:
+ hotword_list = None
+ # for local txt inputs
+ elif os.path.exists(hotword_list_or_file) and hotword_list_or_file.endswith('.txt'):
+ logging.info("Attempting to parse hotwords from local txt...")
+ hotword_list = []
+ hotword_str_list = []
+ with codecs.open(hotword_list_or_file, 'r') as fin:
+ for line in fin.readlines():
+ hw = line.strip()
+ hotword_str_list.append(hw)
+ hotword_list.append(self.converter.tokens2ids([i for i in hw]))
+ hotword_list.append([self.asr_model.sos])
+ hotword_str_list.append('<s>')
+ logging.info("Initialized hotword list from file: {}, hotword list: {}."
+ .format(hotword_list_or_file, hotword_str_list))
+ # for url, download and generate txt
+ elif hotword_list_or_file.startswith('http'):
+ logging.info("Attempting to parse hotwords from url...")
+ work_dir = tempfile.TemporaryDirectory().name
+ if not os.path.exists(work_dir):
+ os.makedirs(work_dir)
+ text_file_path = os.path.join(work_dir, os.path.basename(hotword_list_or_file))
+ local_file = requests.get(hotword_list_or_file)
+ open(text_file_path, "wb").write(local_file.content)
+ hotword_list_or_file = text_file_path
+ hotword_list = []
+ hotword_str_list = []
+ with codecs.open(hotword_list_or_file, 'r') as fin:
+ for line in fin.readlines():
+ hw = line.strip()
+ hotword_str_list.append(hw)
+ hotword_list.append(self.converter.tokens2ids([i for i in hw]))
+ hotword_list.append([self.asr_model.sos])
+ hotword_str_list.append('<s>')
+ logging.info("Initialized hotword list from file: {}, hotword list: {}."
+ .format(hotword_list_or_file, hotword_str_list))
+ # for text str input
+ elif not hotword_list_or_file.endswith('.txt'):
+ logging.info("Attempting to parse hotwords as str...")
+ hotword_list = []
+ hotword_str_list = []
+ for hw in hotword_list_or_file.strip().split():
+ hotword_str_list.append(hw)
+ hotword_list.append(self.converter.tokens2ids([i for i in hw]))
+ hotword_list.append([self.asr_model.sos])
+ hotword_str_list.append('<s>')
+ logging.info("Hotword list: {}.".format(hotword_str_list))
+ else:
+ hotword_list = None
+ return hotword_list
+
+class Speech2TextExport:
+ """Speech2TextExport class
+
+ """
+
+ def __init__(
+ self,
+ asr_train_config: Union[Path, str] = None,
+ asr_model_file: Union[Path, str] = None,
+ cmvn_file: Union[Path, str] = None,
+ lm_train_config: Union[Path, str] = None,
+ lm_file: Union[Path, str] = None,
+ token_type: str = None,
+ bpemodel: str = None,
+ device: str = "cpu",
+ maxlenratio: float = 0.0,
+ minlenratio: float = 0.0,
+ dtype: str = "float32",
+ beam_size: int = 20,
+ ctc_weight: float = 0.5,
+ lm_weight: float = 1.0,
+ ngram_weight: float = 0.9,
+ penalty: float = 0.0,
+ nbest: int = 1,
+ frontend_conf: dict = None,
+ hotword_list_or_file: str = None,
+ **kwargs,
+ ):
+
+ # 1. Build ASR model
+ asr_model, asr_train_args = ASRTask.build_model_from_file(
+ asr_train_config, asr_model_file, cmvn_file, device
+ )
+ frontend = None
+ if asr_train_args.frontend is not None and asr_train_args.frontend_conf is not None:
+ frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf)
+
+ logging.info("asr_model: {}".format(asr_model))
+ logging.info("asr_train_args: {}".format(asr_train_args))
+ asr_model.to(dtype=getattr(torch, dtype)).eval()
+
+ token_list = asr_model.token_list
+
+
+
+ logging.info(f"Decoding device={device}, dtype={dtype}")
+
+ # 5. [Optional] Build Text converter: e.g. bpe-sym -> Text
+ if token_type is None:
+ token_type = asr_train_args.token_type
+ if bpemodel is None:
+ bpemodel = asr_train_args.bpemodel
+
+ if token_type is None:
+ tokenizer = None
+ elif token_type == "bpe":
+ if bpemodel is not None:
+ tokenizer = build_tokenizer(token_type=token_type, bpemodel=bpemodel)
+ else:
+ tokenizer = None
+ else:
+ tokenizer = build_tokenizer(token_type=token_type)
+ converter = TokenIDConverter(token_list=token_list)
+ logging.info(f"Text tokenizer: {tokenizer}")
+
+ # self.asr_model = asr_model
+ self.asr_train_args = asr_train_args
+ self.converter = converter
+ self.tokenizer = tokenizer
+
+ self.device = device
+ self.dtype = dtype
+ self.nbest = nbest
+ self.frontend = frontend
+
+ model = Paraformer_export(asr_model, onnx=False)
+ self.asr_model = model
+
@torch.no_grad()
def __call__(
self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None
@@ -195,76 +453,62 @@
if isinstance(speech, np.ndarray):
speech = torch.tensor(speech)
- # data: (Nsamples,) -> (1, Nsamples)
- # lengths: (1,)
- if len(speech.size()) < 3:
- speech = speech.unsqueeze(0).to(getattr(torch, self.dtype))
- speech_lengths = speech.new_full([1], dtype=torch.long, fill_value=speech.size(1))
- lfr_factor = max(1, (speech.size()[-1]//80)-1)
-
- batch = {"speech": speech, "speech_lengths": speech_lengths}
+ if self.frontend is not None:
+ feats, feats_len = self.frontend.forward(speech, speech_lengths)
+ feats = to_device(feats, device=self.device)
+ feats_len = feats_len.int()
+ self.asr_model.frontend = None
+ else:
+ feats = speech
+ feats_len = speech_lengths
+
+ enc_len_batch_total = feats_len.sum()
+ lfr_factor = max(1, (feats.size()[-1] // 80) - 1)
+ batch = {"speech": feats, "speech_lengths": feats_len}
# a. To device
batch = to_device(batch, device=self.device)
- # b. Forward Encoder
- enc, enc_len = self.asr_model.encode(**batch)
- if isinstance(enc, tuple):
- enc = enc[0]
- # assert len(enc) == 1, len(enc)
- enc_len_batch_total = torch.sum(enc_len).item()
-
- predictor_outs = self.asr_model.calc_predictor(enc, enc_len)
- pre_acoustic_embeds, pre_token_length = predictor_outs[0], predictor_outs[1]
- pre_token_length = pre_token_length.round().long()
- decoder_outs = self.asr_model.cal_decoder_with_predictor(enc, enc_len, pre_acoustic_embeds, pre_token_length)
+ decoder_outs = self.asr_model(**batch)
decoder_out, ys_pad_lens = decoder_outs[0], decoder_outs[1]
-
+
results = []
b, n, d = decoder_out.size()
for i in range(b):
- x = enc[i, :enc_len[i], :]
- am_scores = decoder_out[i, :pre_token_length[i], :]
- if self.beam_search is not None:
- nbest_hyps = self.beam_search(
- x=x, am_scores=am_scores, maxlenratio=self.maxlenratio, minlenratio=self.minlenratio
- )
-
- nbest_hyps = nbest_hyps[: self.nbest]
- else:
- yseq = am_scores.argmax(dim=-1)
- score = am_scores.max(dim=-1)[0]
- score = torch.sum(score, dim=-1)
- # pad with mask tokens to ensure compatibility with sos/eos tokens
- yseq = torch.tensor(
- [self.asr_model.sos] + yseq.tolist() + [self.asr_model.eos], device=yseq.device
- )
- nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
-
+ am_scores = decoder_out[i, :ys_pad_lens[i], :]
+
+ yseq = am_scores.argmax(dim=-1)
+ score = am_scores.max(dim=-1)[0]
+ score = torch.sum(score, dim=-1)
+ # pad with mask tokens to ensure compatibility with sos/eos tokens
+ yseq = torch.tensor(
+ yseq.tolist(), device=yseq.device
+ )
+ nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
+
for hyp in nbest_hyps:
assert isinstance(hyp, (Hypothesis)), type(hyp)
-
+
# remove sos/eos and get results
last_pos = -1
if isinstance(hyp.yseq, list):
token_int = hyp.yseq[1:last_pos]
else:
token_int = hyp.yseq[1:last_pos].tolist()
-
+
# remove blank symbol id, which is assumed to be 0
- token_int = list(filter(lambda x: x != 0, token_int))
-
+ token_int = list(filter(lambda x: x != 0 and x != 2, token_int))
+
# Change integer-ids to tokens
token = self.converter.ids2tokens(token_int)
-
+
if self.tokenizer is not None:
text = self.tokenizer.tokens2text(token)
else:
text = None
-
+
results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
- # assert check_return_type(results)
return results
@@ -281,7 +525,8 @@
data_path_and_name_and_type,
asr_train_config: Optional[str],
asr_model_file: Optional[str],
- audio_lists: Union[List[Any], bytes] = None,
+ cmvn_file: Optional[str] = None,
+ raw_inputs: Union[np.ndarray, torch.Tensor] = None,
lm_train_config: Optional[str] = None,
lm_file: Optional[str] = None,
token_type: Optional[str] = None,
@@ -296,9 +541,74 @@
ngram_weight: float = 0.9,
nbest: int = 1,
num_workers: int = 1,
- frontend_conf: dict = None,
- fs: Union[dict, int] = 16000,
- lang: Optional[str] = None,
+ timestamp_infer_config: Union[Path, str] = None,
+ timestamp_model_file: Union[Path, str] = None,
+ **kwargs,
+):
+ inference_pipeline = inference_modelscope(
+ maxlenratio=maxlenratio,
+ minlenratio=minlenratio,
+ batch_size=batch_size,
+ beam_size=beam_size,
+ ngpu=ngpu,
+ ctc_weight=ctc_weight,
+ lm_weight=lm_weight,
+ penalty=penalty,
+ log_level=log_level,
+ asr_train_config=asr_train_config,
+ asr_model_file=asr_model_file,
+ cmvn_file=cmvn_file,
+ raw_inputs=raw_inputs,
+ lm_train_config=lm_train_config,
+ lm_file=lm_file,
+ token_type=token_type,
+ key_file=key_file,
+ word_lm_train_config=word_lm_train_config,
+ bpemodel=bpemodel,
+ allow_variable_data_keys=allow_variable_data_keys,
+ streaming=streaming,
+ output_dir=output_dir,
+ dtype=dtype,
+ seed=seed,
+ ngram_weight=ngram_weight,
+ nbest=nbest,
+ num_workers=num_workers,
+
+ **kwargs,
+ )
+ return inference_pipeline(data_path_and_name_and_type, raw_inputs)
+
+
+def inference_modelscope(
+ maxlenratio: float,
+ minlenratio: float,
+ batch_size: int,
+ beam_size: int,
+ ngpu: int,
+ ctc_weight: float,
+ lm_weight: float,
+ penalty: float,
+ log_level: Union[int, str],
+ # data_path_and_name_and_type,
+ asr_train_config: Optional[str],
+ asr_model_file: Optional[str],
+ cmvn_file: Optional[str] = None,
+ lm_train_config: Optional[str] = None,
+ lm_file: Optional[str] = None,
+ token_type: Optional[str] = None,
+ key_file: Optional[str] = None,
+ word_lm_train_config: Optional[str] = None,
+ bpemodel: Optional[str] = None,
+ allow_variable_data_keys: bool = False,
+ dtype: str = "float32",
+ seed: int = 0,
+ ngram_weight: float = 0.9,
+ nbest: int = 1,
+ num_workers: int = 1,
+ output_dir: Optional[str] = None,
+ timestamp_infer_config: Union[Path, str] = None,
+ timestamp_model_file: Union[Path, str] = None,
+ param_dict: dict = None,
**kwargs,
):
assert check_argument_types()
@@ -312,51 +622,20 @@
level=log_level,
format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
)
+
+ export_mode = False
+ if param_dict is not None:
+ hotword_list_or_file = param_dict.get('hotword')
+ export_mode = param_dict.get("export_mode", False)
+ else:
+ hotword_list_or_file = None
- if ngpu >= 1:
+ if ngpu >= 1 and torch.cuda.is_available():
device = "cuda"
else:
device = "cpu"
- hop_length: int = 160
- sr: int = 16000
- if isinstance(fs, int):
- sr = fs
- else:
- if 'model_fs' in fs and fs['model_fs'] is not None:
- sr = fs['model_fs']
- # data_path_and_name_and_type for modelscope: (data from audio_lists)
- # ['speech', 'sound', 'am.mvn']
- # data_path_and_name_and_type for funasr:
- # [('/mnt/data/jiangyu.xzy/exp/maas/mvn.1.scp', 'speech', 'kaldi_ark')]
- if isinstance(data_path_and_name_and_type[0], Tuple):
- features_type: str = data_path_and_name_and_type[0][1]
- elif isinstance(data_path_and_name_and_type[0], str):
- features_type: str = data_path_and_name_and_type[1]
- else:
- raise NotImplementedError("unknown features type:{0}".format(data_path_and_name_and_type))
- if features_type != 'sound':
- frontend_conf = None
- flag_modelscope = False
- else:
- flag_modelscope = True
- if frontend_conf is not None:
- if 'hop_length' in frontend_conf:
- hop_length = frontend_conf['hop_length']
+ batch_size = 1
- finish_count = 0
- file_count = 1
- if flag_modelscope and not isinstance(data_path_and_name_and_type[0], Tuple):
- data_path_and_name_and_type_new = [
- audio_lists, data_path_and_name_and_type[0], data_path_and_name_and_type[1]
- ]
- if isinstance(audio_lists, bytes):
- file_count = 1
- else:
- file_count = len(audio_lists)
- if len(data_path_and_name_and_type) >= 3 and frontend_conf is not None:
- mvn_file = data_path_and_name_and_type[2]
- mvn_data = wav_utils.extract_CMVN_featrures(mvn_file)
- frontend_conf['mvn_data'] = mvn_data
# 1. Set random-seed
set_all_random_seed(seed)
@@ -364,6 +643,7 @@
speech2text_kwargs = dict(
asr_train_config=asr_train_config,
asr_model_file=asr_model_file,
+ cmvn_file=cmvn_file,
lm_train_config=lm_train_config,
lm_file=lm_file,
token_type=token_type,
@@ -378,28 +658,48 @@
ngram_weight=ngram_weight,
penalty=penalty,
nbest=nbest,
- frontend_conf=frontend_conf,
+ hotword_list_or_file=hotword_list_or_file,
)
- speech2text = Speech2Text(**speech2text_kwargs)
+ if export_mode:
+ speech2text = Speech2TextExport(**speech2text_kwargs)
+ else:
+ speech2text = Speech2Text(**speech2text_kwargs)
- # 3. Build data-iterator
- if flag_modelscope:
- loader = ASRTask.build_streaming_iterator_modelscope(
- data_path_and_name_and_type_new,
- dtype=dtype,
- batch_size=batch_size,
- key_file=key_file,
- num_workers=num_workers,
- preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
- collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
- allow_variable_data_keys=allow_variable_data_keys,
- inference=True,
- sample_rate=fs
+ if timestamp_model_file is not None:
+ speechtext2timestamp = SpeechText2Timestamp(
+ timestamp_cmvn_file=cmvn_file,
+ timestamp_model_file=timestamp_model_file,
+ timestamp_infer_config=timestamp_infer_config,
)
else:
+ speechtext2timestamp = None
+
+ def _forward(
+ data_path_and_name_and_type,
+ raw_inputs: Union[np.ndarray, torch.Tensor] = None,
+ output_dir_v2: Optional[str] = None,
+ fs: dict = None,
+ param_dict: dict = None,
+ **kwargs,
+ ):
+
+ hotword_list_or_file = None
+ if param_dict is not None:
+ hotword_list_or_file = param_dict.get('hotword')
+ if 'hotword' in kwargs:
+ hotword_list_or_file = kwargs['hotword']
+ if hotword_list_or_file is not None or 'hotword' in kwargs:
+ speech2text.hotword_list = speech2text.generate_hotwords_list(hotword_list_or_file)
+
+ # 3. Build data-iterator
+ if data_path_and_name_and_type is None and raw_inputs is not None:
+ if isinstance(raw_inputs, torch.Tensor):
+ raw_inputs = raw_inputs.numpy()
+ data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
loader = ASRTask.build_streaming_iterator(
data_path_and_name_and_type,
dtype=dtype,
+ fs=fs,
batch_size=batch_size,
key_file=key_file,
num_workers=num_workers,
@@ -409,76 +709,104 @@
inference=True,
)
- forward_time_total = 0.0
- length_total = 0.0
- # 7 .Start for-loop
- # FIXME(kamo): The output format should be discussed about
- asr_result_list = []
- if output_dir is not None:
- writer = DatadirWriter(output_dir)
- else:
- writer = None
+ if param_dict is not None:
+ use_timestamp = param_dict.get('use_timestamp', True)
+ else:
+ use_timestamp = True
- for keys, batch in loader:
- assert isinstance(batch, dict), type(batch)
- assert all(isinstance(s, str) for s in keys), keys
- _bs = len(next(iter(batch.values())))
- assert len(keys) == _bs, f"{len(keys)} != {_bs}"
- # batch = {k: v for k, v in batch.items() if not k.endswith("_lengths")}
+ forward_time_total = 0.0
+ length_total = 0.0
+ finish_count = 0
+ file_count = 1
+ # 7 .Start for-loop
+ # FIXME(kamo): The output format should be discussed about
+ asr_result_list = []
+ output_path = output_dir_v2 if output_dir_v2 is not None else output_dir
+ if output_path is not None:
+ writer = DatadirWriter(output_path)
+ else:
+ writer = None
- logging.info("decoding, utt_id: {}".format(keys))
- # N-best list of (text, token, token_int, hyp_object)
+ for keys, batch in loader:
+ assert isinstance(batch, dict), type(batch)
+ assert all(isinstance(s, str) for s in keys), keys
+ _bs = len(next(iter(batch.values())))
+ assert len(keys) == _bs, f"{len(keys)} != {_bs}"
+ # batch = {k: v for k, v in batch.items() if not k.endswith("_lengths")}
- time_beg = time.time()
- results = speech2text(**batch)
- time_end = time.time()
- forward_time = time_end - time_beg
- lfr_factor = results[0][-1]
- length = results[0][-2]
- forward_time_total += forward_time
- length_total += length
- logging.info(
- "decoding, feature length: {}, forward_time: {:.4f}, rtf: {:.4f}".
- format(length, forward_time, 100 * forward_time / (length*lfr_factor)))
-
- for batch_id in range(_bs):
- result = [results[batch_id][:-2]]
-
- key = keys[batch_id]
- for n, (text, token, token_int, hyp) in zip(range(1, nbest + 1), result):
- # Create a directory: outdir/{n}best_recog
- if writer is not None:
- ibest_writer = writer[f"{n}best_recog"]
-
- # Write the result to each file
- ibest_writer["token"][key] = " ".join(token)
- ibest_writer["token_int"][key] = " ".join(map(str, token_int))
- ibest_writer["score"][key] = str(hyp.score)
-
- if text is not None:
- text_postprocessed = postprocess_utils.sentence_postprocess(token)
- item = {'key': key, 'value': text_postprocessed}
- asr_result_list.append(item)
- finish_count += 1
- asr_utils.print_progress(finish_count / file_count)
+ logging.info("decoding, utt_id: {}".format(keys))
+ # N-best list of (text, token, token_int, hyp_object)
+
+ time_beg = time.time()
+ results = speech2text(**batch)
+ if len(results) < 1:
+ hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
+ results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest
+ time_end = time.time()
+ forward_time = time_end - time_beg
+ lfr_factor = results[0][-1]
+ length = results[0][-2]
+ forward_time_total += forward_time
+ length_total += length
+ rtf_cur = "decoding, feature length: {}, forward_time: {:.4f}, rtf: {:.4f}".format(length, forward_time, 100 * forward_time / (length * lfr_factor))
+ logging.info(rtf_cur)
+
+ for batch_id in range(_bs):
+ result = [results[batch_id][:-2]]
+
+ key = keys[batch_id]
+ for n, result in zip(range(1, nbest + 1), result):
+ text, token, token_int, hyp = result[0], result[1], result[2], result[3]
+ timestamp = None if len(result) < 5 else result[4]
+ # conduct timestamp prediction here
+ # timestamp inference requires token length
+ # thus following inference cannot be conducted in batch
+ if timestamp is None and speechtext2timestamp:
+ ts_batch = {}
+ ts_batch['speech'] = batch['speech'][batch_id].unsqueeze(0)
+ ts_batch['speech_lengths'] = torch.tensor([batch['speech_lengths'][batch_id]])
+ ts_batch['text_lengths'] = torch.tensor([len(token)])
+ us_alphas, us_peaks = speechtext2timestamp(**ts_batch)
+ ts_str, timestamp = ts_prediction_lfr6_standard(us_alphas[0], us_peaks[0], token, force_time_shift=-3.0)
+ # Create a directory: outdir/{n}best_recog
if writer is not None:
- ibest_writer["text"][key] = text
-
- logging.info("decoding, utt: {}, predictions: {}".format(key, text))
+ ibest_writer = writer[f"{n}best_recog"]
- logging.info("decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".
- format(length_total, forward_time_total, 100 * forward_time_total / (length_total*lfr_factor)))
- return asr_result_list
+ # Write the result to each file
+ ibest_writer["token"][key] = " ".join(token)
+ # ibest_writer["token_int"][key] = " ".join(map(str, token_int))
+ ibest_writer["score"][key] = str(hyp.score)
+ ibest_writer["rtf"][key] = rtf_cur
+ if text is not None:
+ if use_timestamp and timestamp is not None:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token, timestamp)
+ else:
+ postprocessed_result = postprocess_utils.sentence_postprocess(token)
+ timestamp_postprocessed = ""
+ if len(postprocessed_result) == 3:
+ text_postprocessed, timestamp_postprocessed, word_lists = postprocessed_result[0], \
+ postprocessed_result[1], \
+ postprocessed_result[2]
+ else:
+ text_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1]
+ item = {'key': key, 'value': text_postprocessed}
+ if timestamp_postprocessed != "":
+ item['timestamp'] = timestamp_postprocessed
+ asr_result_list.append(item)
+ finish_count += 1
+ # asr_utils.print_progress(finish_count / file_count)
+ if writer is not None:
+ ibest_writer["text"][key] = " ".join(word_lists)
-def set_parameters(language: str = None,
- sample_rate: Union[int, Dict[Any, int]] = None):
- if language is not None:
- global global_asr_language
- global_asr_language = language
- if sample_rate is not None:
- global global_sample_rate
- global_sample_rate = sample_rate
+ logging.info("decoding, utt: {}, predictions: {}".format(key, text))
+ rtf_avg = "decoding, feature length total: {}, forward_time total: {:.4f}, rtf avg: {:.4f}".format(length_total, forward_time_total, 100 * forward_time_total / (length_total * lfr_factor))
+ logging.info(rtf_avg)
+ if writer is not None:
+ ibest_writer["rtf"]["rtf_avf"] = rtf_avg
+ return asr_result_list
+
+ return _forward
def get_parser():
@@ -517,12 +845,17 @@
default=1,
help="The number of workers used for DataLoader",
)
-
+ parser.add_argument(
+ "--hotword",
+ type=str_or_none,
+ default=None,
+ help="hotword file path or hotwords seperated by space"
+ )
group = parser.add_argument_group("Input data related")
group.add_argument(
"--data_path_and_name_and_type",
type=str2triple_str,
- required=True,
+ required=False,
action="append",
)
group.add_argument("--key_file", type=str_or_none)
@@ -538,6 +871,11 @@
"--asr_model_file",
type=str,
help="ASR model parameter file",
+ )
+ group.add_argument(
+ "--cmvn_file",
+ type=str,
+ help="Global cmvn file",
)
group.add_argument(
"--lm_train_config",
@@ -613,7 +951,7 @@
default=None,
help="",
)
- group.add_argument("--audio_lists", type=list, default=None)
+ group.add_argument("--raw_inputs", type=list, default=None)
# example=[{'key':'EdevDEWdIYQ_0021','file':'/mnt/data/jiangyu.xzy/test_data/speech_io/SPEECHIO_ASR_ZH00007_zhibodaihuo/wav/EdevDEWdIYQ_0021.wav'}])
group = parser.add_argument_group("Text converter related")
@@ -640,10 +978,22 @@
print(get_commandline_args(), file=sys.stderr)
parser = get_parser()
args = parser.parse_args(cmd)
+ param_dict = {'hotword': args.hotword}
kwargs = vars(args)
kwargs.pop("config", None)
+ kwargs['param_dict'] = param_dict
inference(**kwargs)
if __name__ == "__main__":
main()
+
+ # from modelscope.pipelines import pipeline
+ # from modelscope.utils.constant import Tasks
+ #
+ # inference_16k_pipline = pipeline(
+ # task=Tasks.auto_speech_recognition,
+ # model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch')
+ #
+ # rec_result = inference_16k_pipline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')
+ # print(rec_result)
--
Gitblit v1.9.1