| | |
|---|
| | | ) |
|---|
| | | |
|---|
| | | self.blank_id = blank_id |
|---|
| | | self.sos = sos if sos is not None else vocab_size - 1 |
|---|
| | | self.eos = eos if eos is not None else vocab_size - 1 |
|---|
| | | self.sos = vocab_size - 1 |
|---|
| | | self.eos = vocab_size - 1 |
|---|
| | | self.vocab_size = vocab_size |
|---|
| | | self.ignore_id = ignore_id |
|---|
| | | self.ctc_weight = ctc_weight |
|---|
| | |
|---|
| | | text: (Batch, Length) |
|---|
| | | text_lengths: (Batch,) |
|---|
| | | """ |
|---|
| | | # import pdb; |
|---|
| | | # pdb.set_trace() |
|---|
| | | |
|---|
| | | if len(text_lengths.size()) > 1: |
|---|
| | | text_lengths = text_lengths[:, 0] |
|---|
| | | if len(speech_lengths.size()) > 1: |
|---|
| | |
|---|
| | | scorers["ngram"] = ngram |
|---|
| | | |
|---|
| | | weights = dict( |
|---|
| | | decoder=1.0 - kwargs.get("decoding_ctc_weight", 0.5), |
|---|
| | | ctc=kwargs.get("decoding_ctc_weight", 0.5), |
|---|
| | | decoder=1.0 - kwargs.get("decoding_ctc_weight", 0.3), |
|---|
| | | ctc=kwargs.get("decoding_ctc_weight", 0.3), |
|---|
| | | lm=kwargs.get("lm_weight", 0.0), |
|---|
| | | ngram=kwargs.get("ngram_weight", 0.0), |
|---|
| | | length_bonus=kwargs.get("penalty", 0.0), |
|---|
| | | ) |
|---|
| | | beam_search = BeamSearch( |
|---|
| | | beam_size=kwargs.get("beam_size", 10), |
|---|
| | | beam_size=kwargs.get("beam_size", 20), |
|---|
| | | weights=weights, |
|---|
| | | scorers=scorers, |
|---|
| | | sos=self.sos, |
|---|
| | |
|---|
| | | time2 = time.perf_counter() |
|---|
| | | meta_data["load_data"] = f"{time2 - time1:0.3f}" |
|---|
| | | audio_sample_list = sample_list[0] |
|---|
| | | ocr_sample_list = sample_list[1] |
|---|
| | | if len(sample_list) >1: |
|---|
| | | ocr_sample_list = sample_list[1] |
|---|
| | | else: |
|---|
| | | ocr_sample_list = [[294, 0]] |
|---|
| | | speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), |
|---|
| | | frontend=frontend) |
|---|
| | | time3 = time.perf_counter() |
|---|
| | |
|---|
| | | |
|---|
| | | 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] |
|---|
| | | pdb.set_trace() |
|---|
| | | ocr = ocr_sample_list[0] |
|---|
| | | ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1)) |
|---|
| | | |
|---|
| | | 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).to(device=kwargs["device"]) |
|---|
| | | ocr_lengths = ocr.new_full([1], dtype=torch.long, fill_value=ocr.size(1)).to(device=kwargs["device"]) |
|---|
| | | ocr, ocr_lens, _ = self.text_encoder(ocr, ocr_lengths) |
|---|
| | | pdb.set_trace() |
|---|
| | | fusion_out, _, _, _ = self.fusion_encoder(encoder_out,None, ocr, None) |
|---|
| | | encoder_out = encoder_out + fusion_out |
|---|
| | | # 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] |
|---|
| | | |
|---|
| | | |
|---|
| | | results = [] |
|---|
| | | b, n, d = encoder_out.size() |
|---|
| | |
|---|
| | | # Change integer-ids to tokens |
|---|
| | | token = tokenizer.ids2tokens(token_int) |
|---|
| | | text = tokenizer.tokens2text(token) |
|---|
| | | |
|---|
| | | |
|---|
| | | text_postprocessed, _ = postprocess_utils.sentence_postprocess(token) |
|---|
| | | result_i = {"key": key[i], "token": token, "text": text_postprocessed} |
|---|
| | | results.append(result_i) |
|---|
