| 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. | |
| See [main repository](https://github.com/Plachtaa/FAcodec) for example usages. |