mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
update
This commit is contained in:
游雁
parent
5ddad6db68
commit
2849886bb5
@ -364,201 +364,6 @@ class Speech2VadSegment:
|
||||
return fbanks, segments
|
||||
|
||||
|
||||
# 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,
|
||||
# vad_infer_config: Optional[str] = None,
|
||||
# vad_model_file: Optional[str] = None,
|
||||
# vad_cmvn_file: Optional[str] = None,
|
||||
# time_stamp_writer: bool = False,
|
||||
# punc_infer_config: Optional[str] = None,
|
||||
# punc_model_file: 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 speech2vadsegment
|
||||
# speech2vadsegment_kwargs = dict(
|
||||
# vad_infer_config=vad_infer_config,
|
||||
# vad_model_file=vad_model_file,
|
||||
# vad_cmvn_file=vad_cmvn_file,
|
||||
# device=device,
|
||||
# dtype=dtype,
|
||||
# )
|
||||
# # logging.info("speech2vadsegment_kwargs: {}".format(speech2vadsegment_kwargs))
|
||||
# speech2vadsegment = Speech2VadSegment(**speech2vadsegment_kwargs)
|
||||
#
|
||||
# # 3. 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)
|
||||
#
|
||||
# text2punc = Text2Punc(punc_infer_config, punc_model_file, device=device, dtype=dtype)
|
||||
#
|
||||
# # 3. Build data-iterator
|
||||
# loader = ASRTask.build_streaming_iterator(
|
||||
# data_path_and_name_and_type,
|
||||
# dtype=dtype,
|
||||
# batch_size=1,
|
||||
# key_file=key_file,
|
||||
# num_workers=num_workers,
|
||||
# preprocess_fn=VADTask.build_preprocess_fn(speech2vadsegment.vad_infer_args, False),
|
||||
# collate_fn=VADTask.build_collate_fn(speech2vadsegment.vad_infer_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
|
||||
# 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()
|
||||
# vad_results = speech2vadsegment(**batch)
|
||||
# time_end = time.time()
|
||||
# fbanks, vadsegments = vad_results[0], vad_results[1]
|
||||
# for i, segments in enumerate(vadsegments):
|
||||
# result_segments = [["", [], [], ]]
|
||||
# for j, segment_idx in enumerate(segments):
|
||||
# bed_idx, end_idx = int(segment_idx[0]/10), int(segment_idx[1]/10)
|
||||
# segment = fbanks[:, bed_idx:end_idx, :].to(device)
|
||||
# speech_lengths = torch.Tensor([end_idx-bed_idx]).int().to(device)
|
||||
# batch = {"speech": segment, "speech_lengths": speech_lengths, "begin_time": vadsegments[i][j][0], "end_time": vadsegments[i][j][1]}
|
||||
# results = speech2text(**batch)
|
||||
# if len(results) < 1:
|
||||
# hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
|
||||
# results = [[" ", ["<space>"], [2], 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)))
|
||||
# result_cur = [results[0][:-2]]
|
||||
# if j == 0:
|
||||
# result_segments = result_cur
|
||||
# else:
|
||||
# result_segments = [[result_segments[0][i] + result_cur[0][i] for i in range(len(result_cur[0]))]]
|
||||
#
|
||||
# key = keys[0]
|
||||
# result = result_segments[0]
|
||||
# text, token, token_int, time_stamp = result
|
||||
#
|
||||
# # Create a directory: outdir/{n}best_recog
|
||||
# if writer is not None:
|
||||
# ibest_writer = writer[f"1best_recog"]
|
||||
#
|
||||
# # Write the result to each file
|
||||
# ibest_writer["token"][key] = " ".join(token)
|
||||
# ibest_writer["token_int"][key] = " ".join(map(str, token_int))
|
||||
#
|
||||
# if text is not None:
|
||||
# postprocessed_result = postprocess_utils.sentence_postprocess(token, time_stamp)
|
||||
# if len(postprocessed_result) == 3:
|
||||
# text_postprocessed, time_stamp_postprocessed, word_lists = postprocessed_result[0], postprocessed_result[1], postprocessed_result[2]
|
||||
# text_postprocessed_punc, punc_id_list = text2punc(word_lists, 20)
|
||||
# text_postprocessed_punc_time_stamp = "predictions: {} time_stamp: {}".format(text_postprocessed_punc, time_stamp_postprocessed)
|
||||
# else:
|
||||
# text_postprocessed = postprocessed_result
|
||||
# time_stamp_postprocessed = None
|
||||
# word_lists = None
|
||||
# text_postprocessed_punc_time_stamp = None
|
||||
# punc_id_list = None
|
||||
#
|
||||
# item = {'key': key, 'value': text_postprocessed_punc_time_stamp, 'text': text_postprocessed, 'time_stamp': time_stamp_postprocessed, 'punc': punc_id_list}
|
||||
# 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_postprocessed
|
||||
# if time_stamp_writer and time_stamp_postprocessed is not None:
|
||||
# ibest_writer["time_stamp"][key] = " ".join(["-".join(map(str, ts)) for ts in time_stamp_postprocessed])
|
||||
#
|
||||
# logging.info("decoding, utt: {}, predictions: {}, time_stamp: {}".format(key, text_postprocessed_punc, time_stamp_postprocessed))
|
||||
#
|
||||
# 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,
|
||||
|
||||
Loading…
Reference in New Issue
Block a user