bhetherman/live-voice-chat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
12 Commits 2 Branches 0 Tags
56923ff424386f7b5db6c97796eb3cd5ca2e6142
Commit Graph

6 Commits

Author SHA1 Message Date
bhetherman fcf0be38bc t5 encoder fp8 seems to be working 2026-04-12 13:50:34 -04:00
bhetherman 2818b41004 first stab at adding video 2026-04-12 04:11:52 -04:00
bhetherman 680c5b04cc Pre-download the spacy model that kokoro needs at runtime 2026-04-08 11:43:26 -04:00
bhetherman c07187aae1 add readme, remove torchvision 2026-04-08 04:08:42 -04:00
bhetherman 263f39e0a3 Switch to CUDA 12.8 + ONNX-based VAD for RTX 5090 Blackwell support 
Upgrade PyTorch to 2.7+ with cu128 wheels for Blackwell (sm_120) GPU
support. Replace silero-vad (which depends on torchaudio) with a direct
ONNX Runtime implementation of the same Silero VAD model, eliminating
the torchaudio dependency entirely.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-08 04:01:27 -04:00
bhetherman 0305f1dccd updates for docker take 1 2026-04-08 03:05:26 -04:00