russell@unturf.com
a148088cb0
- 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
12 lines
No EOL
324 B
Bash
12 lines
No EOL
324 B
Bash
TTS_HOME=voices
|
|
HF_HOME=voices
|
|
|
|
# Worker processes for concurrent TTS requests
|
|
# Use WORKERS=1 for GPU models like Qwen3-TTS (each worker loads its own model copy)
|
|
# Use WORKERS=4 for CPU models like Piper
|
|
WORKERS=1
|
|
|
|
#PRELOAD_MODEL=xtts
|
|
#PRELOAD_MODEL=xtts_v2.0.2
|
|
#EXTRA_ARGS=--log-level DEBUG --unload-timer 300
|
|
#USE_ROCM=1 |