Liumeng Xue

@HeCheng0625 Please follow up on this issue.

Thanks for your feedback. There is a argument `resume` [here](https://github.com/open-mmlab/Amphion/blob/4542a2d7c1e071e5d10b2d3c285bd1383d0f2292/bins/tts/train.py#L57) that can continue training from the last epoch. We'll update the VITS receipt asap to make the usage more convenient.

I noticed that you are using macOS with MPS, but you are still using `CUDA_VISIBLE_DEVICES` to assign the device. It might be worth considering using `PYTORCH_ENABLE_MPS_FALLBACK` instead to assign the...

> * fixed fs2 24k training and inference issues, fixed hifigan vocoder training > * aligned mels feature for acoustic model and vocoder, so that people can use the pretrained...

Yes, please take a look at the response to issue #62 for more information.

> HI, I found that resume code of TTS is in https://github.com/open-mmlab/Amphion/blob/main/models/tts/base/tts_trainer.py#L140 and https://github.com/open-mmlab/Amphion/blob/main/models/tts/base/tts_trainer.py#L302 > > however, _accelerator_prepare is in https://github.com/open-mmlab/Amphion/blob/main/models/tts/base/tts_trainer.py#L145 > > So when resume_type=="resume", self. _check_resume function seems...

> For another issue, I am confused with the `phon_id_collator.get_phone_id_sequence` when i run the infer process with `sh egs/tts/VITS/run.sh --stage 3 --gpu "0" \ --config ckpts/tts/vits_ljspeech/args.json \ --infer_expt_dir ckpts/tts/vits_ljspeech/ \...

Could you please give some your samples?

Thanks for your efforts. There are some suggestions for a standard PR, especially for the PR that integrates a new model into Amphion: - Please format the code using `black`...

Hi @happysalada, please check out #140, we released a docker image to support the docker installation.