drlor2k

Thanks for your response @v-nhandt21, I tried https://github.com/thinhlpg/vixtts-demo, it's a great attempt but it lacks the necessary stability. I actually forgot that I could fine-tune it :v

hello @v-nhandt21, I have some takeaways from VITS2 and XTTS, can you give your opinion? 1. In terms of sound output quality, VITS may be better than XTTS. 2. XTTS...

Thank you for your response @v-nhandt21, I have another question, can you help me? I see that some speech2speech repo uses a very small `val dataset` (2 records each voice),...

thanks @aluminumbox for the reply, one more question! My German dataset is a bit mixed with English, is this ok? Or should I use a pure German dataset.

> Try using something like this: > > ```python > text = f"" + data["sentence"].strip() > ``` Hi @MiXaiLL76 , do you mean when adding a new language my data...

I think the author will update the code for this issue, however I have a temporary solution you can refer to. 1. When starting a new training session, you need...

I thought the above code would make `step` go back to `current_step` when starting a new epoch. I modified it a bit. ``` # Save init checkpoints info_dict = deepcopy(configs['train_conf'])...

Yes, you need to modify the `current_epoch` and `current_step` values ​​in `cosyvoice.fromscratch.yaml` every time you resume training from a checkpoint. You can see `current_epoch` and `current_step` in the checkpoint filename....

hello @rlenain, are you training only llm model or also flow model? and how much GPU resources you use for Spanish training.