| | |
|---|
| | | self.converter = converter |
|---|
| | | self.tokenizer = tokenizer |
|---|
| | | 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}") |
|---|
| | |
|---|
| | | 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 [] |
|---|
| | | 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] |
|---|
| | | |
|---|
| | |
|---|
| | | # 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] |
|---|
| | |
|---|
| | | nbest: int = 1, |
|---|
| | | num_workers: int = 1, |
|---|
| | | output_dir: Optional[str] = None, |
|---|
| | | param_dict: dict = None, |
|---|
| | | **kwargs, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | |
|---|
| | | data_path_and_name_and_type, |
|---|
| | | raw_inputs: Union[np.ndarray, torch.Tensor] = None, |
|---|
| | | output_dir_v2: Optional[str] = None, |
|---|
| | | param_dict: dict = None, |
|---|
| | | ): |
|---|
| | | # 3. Build data-iterator |
|---|
| | | if data_path_and_name_and_type is None and raw_inputs is not None: |
|---|
| | |
|---|
| | | 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] |
|---|
