fish-diffusion

fish-diffusion copied to clipboard

updates: - [github.com/pycqa/isort: 5.12.0 → 6.0.1](https://github.com/pycqa/isort/compare/5.12.0...6.0.1) - [github.com/psf/black: 23.10.1 → 25.1.0](https://github.com/psf/black/compare/23.10.1...25.1.0) - [github.com/codespell-project/codespell: v2.2.6 → v2.4.1](https://github.com/codespell-project/codespell/compare/v2.2.6...v2.4.1)

pre-commit-ci[bot]

CUDA bfloat16 problem

4

``` 2023-10-23 10:49:30,409 WARNING: logs/HiFiSVC doesn't exist yet! Global seed set to 594461 Using bfloat16 Automatic Mixed Precision (AMP) GPU available: True (cuda), used: True TPU available: False, using: 0...

A-2-H

Have confusion about different model arch

1

If I trained a model by using `svc_content_vec.py`, can I use the model trained by SVC method for SVS? If I can't, what's the difference between diffsinger with diffsinger-svc?

Yurzi

Add Hop256 Support And BigVGan Snake structure

1

NSF hifigan with snake is not supported by ONNX 1.13

catalystfrank

maybe can add rmvpe method?

blane187gt

我想试着跑一下训练，但是一直卡在Sanity Checking DataLoader这里（几十分钟还没动静），这是因为我用的CPU吗？ 

great-luao

colstone

AimoneAndex

As in the title. The denoiser script makes input audio very distorted, too loud and clipping. According to guide i used this script: ``` python tools/diffusion/inference.py --config configs/denoiser_cn_hubert.py \ --checkpoint...

A-2-H

Hello, the download link seems to be unavailable: https://github.com/fishaudio/chinese-hubert-soft/releases/download/v1/chinese-hubert-soft-v1.ckpt. Could you please check or provide an updated link?

dyyoungg