| | |
|---|
| | | fbank_beg.append(fbank_beg_i) |
|---|
| | | |
|---|
| | | if len(input_ids) > self.max_token_length: |
|---|
| | | logging.info( |
|---|
| | | f"input_ids > max_token_length: {len(input_ids)}>{self.max_token_length}, {item}" |
|---|
| | | ) |
|---|
| | | badcase_flag = True |
|---|
| | | if badcase_flag: |
|---|
| | | continue |
|---|
| | | input_ids = torch.tensor(input_ids, dtype=torch.int64) # [: self.max_token_length] |
|---|
| | | attention_mask = torch.tensor([len(input_ids)], dtype=torch.int32) |
|---|
| | | attention_mask = torch.tensor([1] * len(input_ids), dtype=torch.int32) |
|---|
| | | labels = torch.tensor(labels, dtype=torch.int64) # [: self.max_token_length] |
|---|
| | | |
|---|
| | | fbank = speech[0, :, :] |
|---|
