Open-source State-of-the-art TTS model which runs on a CPU 😻
Python
Commits on main
Audio decoder and voice cloning: less GPU memory, and AMD GPUs
a6936f5 haaziq-sl committed 27 days ago
Merge pull request #174 from stellon-admin/fix/penalize-silence-token
bd359e5 Kitten committed 29 days ago
Rename KittenML_ Expressive AI TTS at a Glance.png to kitten_tts_2_features.png
cd1a5f0 Kitten committed 29 days ago
Rename Kitten-TTS 2 Announcement Banner.png to kitten_tts_2_announcement.png
4c5b1ce Kitten committed 29 days ago
Merge pull request #164 from kevin9327/fix/utf8-json-on-windows
be98ab6 Kitten committed 29 days ago
Load emb4 weights without expanding the whole model in host memory
4168e23 haaziq-sl committed 29 days ago
Add an opt-in float16 fallback for compute capability 7.5 GPUs
67f07be haaziq-sl committed 1 month ago