| | |
|---|
| | | ind: int |
|---|
| | | """ |
|---|
| | | with autocast(False): |
|---|
| | | pdb.set_trace() |
|---|
| | | # Data augmentation |
|---|
| | | if self.specaug is not None and self.training: |
|---|
| | | speech, speech_lengths = self.specaug(speech, speech_lengths) |
|---|
| | | pdb.set_trace() |
|---|
| | | # Normalization for feature: e.g. Global-CMVN, Utterance-CMVN |
|---|
| | | if self.normalize is not None: |
|---|
| | | speech, speech_lengths = self.normalize(speech, speech_lengths) |
|---|
| | | pdb.set_trace() |
|---|
| | | # Forward encoder |
|---|
| | | # feats: (Batch, Length, Dim) |
|---|
| | | # -> encoder_out: (Batch, Length2, Dim2) |
|---|
| | |
|---|
| | | |
|---|
| | | if intermediate_outs is not None: |
|---|
| | | return (encoder_out, intermediate_outs), encoder_out_lens |
|---|
| | | pdb.set_trace() |
|---|
| | | return encoder_out, encoder_out_lens |
|---|
| | | |
|---|
| | | def _calc_att_loss( |
|---|
| | |
|---|
| | | |
|---|
| | | speech = speech.to(device=kwargs["device"]) |
|---|
| | | speech_lengths = speech_lengths.to(device=kwargs["device"]) |
|---|
| | | pdb.set_trace() |
|---|
| | | # Encoder |
|---|
| | | encoder_out, encoder_out_lens = self.encode(speech, speech_lengths) |
|---|
| | | if isinstance(encoder_out, tuple): |
|---|
| | | encoder_out = encoder_out[0] |
|---|
| | | |
|---|
| | | ocr_list_new = [[x + 1 if x != 0 else x for x in sublist] for sublist in ocr_sample_list] |
|---|
| | | ocr = torch.tensor(ocr_list_new) |
|---|
| | | ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1)) |
|---|
| | | ocr, ocr_lens, _ = self.text_encoder(ocr, ocr_lengths) |
|---|
| | | fusion_out, _, _, _ = self.fusion_encoder(encoder_out,None, ocr, None) |
|---|
| | | encoder_out = encoder_out + fusion_out |
|---|
| | | pdb.set_trace() |
|---|
| | | # c. Passed the encoder result and the beam search |
|---|
| | | nbest_hyps = self.beam_search( |
|---|
| | | x=encoder_out[0], maxlenratio=kwargs.get("maxlenratio", 0.0), minlenratio=kwargs.get("minlenratio", 0.0) |
|---|
| | |
|---|
| | | |
|---|
| | | nbest_hyps = nbest_hyps[: self.nbest] |
|---|
| | | |
|---|
| | | |
|---|
| | | pdb.set_trace() |
|---|
| | | results = [] |
|---|
| | | b, n, d = encoder_out.size() |
|---|
| | | for i in range(b): |
|---|
| | |
|---|
| | | # remove blank symbol id, which is assumed to be 0 |
|---|
| | | token_int = list(filter(lambda x: x != self.eos and x != self.sos and x != self.blank_id, token_int)) |
|---|
| | | |
|---|
| | | pdb.set_trace() |
|---|
| | | # Change integer-ids to tokens |
|---|
| | | token = tokenizer.ids2tokens(token_int) |
|---|
| | | pdb.set_trace() |
|---|
| | | text = tokenizer.tokens2text(token) |
|---|
| | | |
|---|
| | | pdb.set_trace() |
|---|
| | | |
|---|
| | | text_postprocessed, _ = postprocess_utils.sentence_postprocess(token) |
|---|
| | | result_i = {"key": key[i], "token": token, "text": text_postprocessed} |
|---|
| | | results.append(result_i) |
|---|
