| | |
|---|
| | | 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, |
|---|
