FAcodec Redecoder
FAcodec trained on 50k hours speech data, with more timbre diversity and better at reconstructing speakers from podcasts, videos, games or animations. This is a separate decoder designed and trained based on the...
Model source
- Kind
- Other
- File size
- 608 MB
- Version
- vRevision fb9893d
- Updated
- Sep 18, 2026
- Downloads
- 0
- Tasks
- Audio
- Source
- Hugging Face
Source description
FAcodec trained on 50k hours speech data, with more timbre diversity and better at reconstructing speakers from podcasts, videos, games or animations.
This is a separate decoder designed and trained based on the pretrained encoder specifically for voice conversion task.
It is capable of zero-shot voice conversion, stream voice conversion and has outstanding timbre generalization ability.
See main repository for example usages.
Sources
1 source
Sources
1 sourceVerified Sep 18
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: mit pipeline_tag: audio-to-audio --- [FAcodec](https://arxiv.org/pdf/2403.03100) trained on 50k hours speech data, with more timbre diversity and better at reconstructing speakers from podcasts, videos, games or animations. This is a separate decoder designed and trained based on the pretrained [encoder](https://huggingface.co/Plachta/FAcodec) specifically for voice conversion task. It is capable of zero-shot voice conversion, stream voice conversion and has outstanding timbre generalization ability. See [main repository](https://github.com/Plachtaa/FAcodec) for example usages.
Source context: 0 downloads · 10 likes · Pipeline audio-to-audio · Repo Plachta/FAcodec-redecoder
