| | |
|---|
| | | |
|---|
| | | 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( |
|---|
| | |
|---|
| | | else: |
|---|
| | | # extract fbank feats |
|---|
| | | time1 = time.perf_counter() |
|---|
| | | pdb.set_trace() |
|---|
| | | sample_list = load_audio_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000), |
|---|
| | | data_type=kwargs.get("data_type", "sound"), |
|---|
| | | tokenizer=tokenizer) |
|---|
| | |
|---|
| | | |
|---|
| | | 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, ocr_lens, _ = self.text_encoder(ocr, ocr_lengths) |
|---|
| | | 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) |
|---|
