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 | 518 +++++++++++++++++++++++++++++++++++++--------------------
1 files changed, 336 insertions(+), 182 deletions(-)
diff --git a/funasr/bin/asr_inference_paraformer.py b/funasr/bin/asr_inference_paraformer.py
index 1a73457..8cbd419 100644
--- 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
@@ -35,15 +40,10 @@
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
-
-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
-}
+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
class Speech2Text:
@@ -51,7 +51,7 @@
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), ...]
@@ -78,6 +78,7 @@
penalty: float = 0.0,
nbest: int = 1,
frontend_conf: dict = None,
+ hotword_list_or_file: str = None,
**kwargs,
):
assert check_argument_types()
@@ -95,10 +96,13 @@
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)),
)
@@ -165,8 +169,13 @@
self.asr_train_args = asr_train_args
self.converter = converter
self.tokenizer = tokenizer
+
+ # 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 and not is_use_lm:
+ 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}")
@@ -178,12 +187,13 @@
self.nbest = nbest
self.frontend = frontend
self.encoder_downsampling_factor = 1
- if asr_train_args.encoder_conf["input_layer"] == "conv2d":
+ 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
+ self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None,
+ begin_time: int = 0, end_time: int = None,
):
"""Inference
@@ -224,8 +234,20 @@
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()
- 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]
+ 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()
@@ -259,7 +281,223 @@
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
+
+ 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
+ ):
+ """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
+
+ 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)
+
+ 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):
+ 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 and x != 2, token_int))
# Change integer-ids to tokens
token = self.converter.ids2tokens(token_int)
@@ -271,165 +509,8 @@
results.append((text, token, token_int, hyp, enc_len_batch_total, lfr_factor))
- # assert check_return_type(results)
return results
-
-# def inference(
-# 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,
-# raw_inputs: Union[np.ndarray, torch.Tensor] = 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,
-# streaming: bool = False,
-# output_dir: Optional[str] = None,
-# dtype: str = "float32",
-# seed: int = 0,
-# 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,
-# **kwargs,
-# ):
-# assert check_argument_types()
-#
-# if word_lm_train_config is not None:
-# raise NotImplementedError("Word LM is not implemented")
-# if ngpu > 1:
-# raise NotImplementedError("only single GPU decoding is supported")
-#
-# logging.basicConfig(
-# level=log_level,
-# format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
-# )
-#
-# if ngpu >= 1 and torch.cuda.is_available():
-# device = "cuda"
-# else:
-# device = "cpu"
-#
-# # 1. Set random-seed
-# set_all_random_seed(seed)
-#
-# # 2. Build speech2text
-# 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,
-# bpemodel=bpemodel,
-# device=device,
-# maxlenratio=maxlenratio,
-# minlenratio=minlenratio,
-# dtype=dtype,
-# beam_size=beam_size,
-# ctc_weight=ctc_weight,
-# lm_weight=lm_weight,
-# ngram_weight=ngram_weight,
-# penalty=penalty,
-# nbest=nbest,
-# frontend_conf=frontend_conf,
-# )
-# speech2text = Speech2Text(**speech2text_kwargs)
-#
-# # 3. Build data-iterator
-# loader = ASRTask.build_streaming_iterator(
-# data_path_and_name_and_type,
-# 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,
-# )
-#
-# 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 = []
-# if output_dir is not None:
-# writer = DatadirWriter(output_dir)
-# else:
-# writer = None
-#
-# 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")}
-#
-# 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 = [[" ", ["<space>"], [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
-# 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)
-# if writer is not None:
-# ibest_writer["text"][key] = text
-#
-# logging.info("decoding, utt: {}, predictions: {}".format(key, text))
-#
-# 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
def inference(
maxlenratio: float,
@@ -460,7 +541,8 @@
ngram_weight: float = 0.9,
nbest: int = 1,
num_workers: int = 1,
-
+ timestamp_infer_config: Union[Path, str] = None,
+ timestamp_model_file: Union[Path, str] = None,
**kwargs,
):
inference_pipeline = inference_modelscope(
@@ -524,6 +606,9 @@
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()
@@ -537,6 +622,13 @@
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 and torch.cuda.is_available():
device = "cuda"
@@ -566,14 +658,39 @@
ngram_weight=ngram_weight,
penalty=penalty,
nbest=nbest,
+ hotword_list_or_file=hotword_list_or_file,
)
- speech2text = Speech2Text(**speech2text_kwargs)
+ if export_mode:
+ speech2text = Speech2TextExport(**speech2text_kwargs)
+ else:
+ speech2text = Speech2Text(**speech2text_kwargs)
+
+ 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):
@@ -582,6 +699,7 @@
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,
@@ -590,6 +708,11 @@
allow_variable_data_keys=allow_variable_data_keys,
inference=True,
)
+
+ if param_dict is not None:
+ use_timestamp = param_dict.get('use_timestamp', True)
+ else:
+ use_timestamp = True
forward_time_total = 0.0
length_total = 0.0
@@ -618,7 +741,7 @@
results = speech2text(**batch)
if len(results) < 1:
hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
- results = [[" ", ["<space>"], [2], hyp, 10, 6]] * nbest
+ results = [[" ", ["sil"], [2], hyp, 10, 6]] * nbest
time_end = time.time()
forward_time = time_end - time_beg
lfr_factor = results[0][-1]
@@ -632,7 +755,19 @@
result = [results[batch_id][:-2]]
key = keys[batch_id]
- for n, (text, token, token_int, hyp) in zip(range(1, nbest + 1), result):
+ 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 = writer[f"{n}best_recog"]
@@ -644,13 +779,25 @@
ibest_writer["rtf"][key] = rtf_cur
if text is not None:
- text_postprocessed = postprocess_utils.sentence_postprocess(token)
+ 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] = text
+ ibest_writer["text"][key] = " ".join(word_lists)
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))
@@ -698,7 +845,12 @@
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",
@@ -826,8 +978,10 @@
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)
--
Gitblit v1.9.1