FAcodec trained on 50k hours speech data, with more timbre diversity and better at reconstructing speakers from podcasts, videos, games or animations.
See main repository for example usages.
FAcodec trained on 50k hours speech data, with more timbre diversity and better at reconstructing speakers from podcasts, videos, games or animations.
See main repository for example usages.
有文件？提交种子。
提交种子