asr-pub

some minor error in python3

Update README.md

1

# Before submitting - [ ] Was this discussed/approved via a Github issue? (no need for typos, doc improvements) - [ ] Did you read the [contributor guideline](https://github.com/pytorch/fairseq/blob/main/CONTRIBUTING.md)? - [...

[Bug] XTTS v2 cond_idxs missing a 'for' loop for training

2

### Describe the bug https://github.com/coqui-ai/TTS/blob/c99e885cc8a35639ca124a6cad9573bb23f06764/TTS/tts/layers/xtts/gpt.py#L543-L546 I think is there lack a for loop? ```python if cond_idxs is not None: for idx in range(cond_idxs.size(0)): cond_start = cond_idxs[idx, 0] cond_end = cond_idxs[idx,...

Hello，I trained a semantic tokens -> acoustic tokens(3 codes) model，and I want to use the argmax to make every inference the same. ```python if argmax: print("use argmax") sampled = torch.argmax(last_coarse_logits,...