| | |
|---|
| | | tokenizer=tokenizer) |
|---|
| | | time2 = time.perf_counter() |
|---|
| | | meta_data["load_data"] = f"{time2 - time1:0.3f}" |
|---|
| | | pdb.set_trace() |
|---|
| | | audio_sample_list = sample_list[0] |
|---|
| | | ocr_sample_list = sample_list[1] |
|---|
| | | speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"), |
|---|
| | |
|---|
| | | encoder_out, encoder_out_lens = self.encode(speech, speech_lengths) |
|---|
| | | if isinstance(encoder_out, tuple): |
|---|
| | | encoder_out = encoder_out[0] |
|---|
| | | |
|---|
| | | pdb.set_trace() |
|---|
| | | 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 = 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) |
|---|
| | | fusion_out, _, _, _ = self.fusion_encoder(encoder_out,None, ocr, None) |
|---|
| | | encoder_out = encoder_out + fusion_out |
|---|
