482b17960c
F5-TTS engine consistency sweep (Makefile, startup, README, docs)
2026-05-24 08:24:38 -04:00
2df34f85cc
Add F5-TTS as tts-1-f5 engine (additive, alongside tts-1-qwen)
2026-05-23 13:24:25 -04:00
a148088cb0
Fix Qwen TTS deadlock, reduce workers to 1 for GPU
...
- Fix subprocess deadlock in Qwen TTS by using threading for stdin write
(prevents pipe buffer deadlock on large audio output)
- Set WORKERS=1 for GPU models to avoid VRAM duplication
(4 workers × 3GB model = OOM, 1 worker works fine)
- Update CLAUDE.md: use git push/pull instead of rsync for deployment
2026-01-26 19:14:19 -05:00
cac40d75d3
Set default workers to 4 to prevent server lockup
2026-01-26 18:23:51 -05:00
0159f1f216
Add configurable WORKERS env var, default to 1 for GPU models
2026-01-26 13:16:44 -05:00
matatonic
ae6a384e75
0.14.0 +streaming, +pcm, +wav, +temp, top_p, etc.
2024-06-26 20:54:24 -04:00
matatonic
72c7b799b9
xtts: +AMD gpu ROCm, +Apple MPS
2024-06-24 20:35:07 -04:00
matatonic
ea4af74e5c
0.13.0 -parler, +arm64, +audio_reader
2024-06-23 12:52:03 -04:00
matatonic
2fcb7cef0f
0.11.0 - Multilingual, new startup & dockerfiles, Fixes : #5 , #6 , #8 , #9
2024-05-29 17:01:11 -04:00
matatonic
6864cf03b1
0.10.0
2024-04-26 20:42:33 -04:00
