5 commits

Author	SHA1	Message	Date
russell@unturf.com	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
russell@unturf.com	0159f1f216	Add configurable WORKERS env var, default to 1 for GPU models	2026-01-26 13:16:44 -05:00
russell@unturf.com	b315659be6	Make Qwen3-TTS the default engine, add CPU-only docker support ... - Switch default TTS engine from Piper to Qwen3-TTS (1.7B params) - Upgrade to Python 3.12 - Add docker-compose.cpu.yml for CPU-only deployments - Improve GPU configuration with NVIDIA environment variables - Comment out optional engines (Piper, XTTS, Silero, Kokoro) in requirements - Update Makefile with local/local-cpu targets and venv support - Simplify voice_to_speaker.default.yaml for Qwen3-TTS voices - Update docs/MODELS.md with Qwen3-TTS documentation - Add git commit guidelines to CLAUDE.md	2026-01-26 10:41:23 -05:00
russell@unturf.com	4a019cf897	Add detailed AGPL v3 license obligations documentation ... Explains source code requirements for network service operators, practical compliance methods, and Raccoon Mission rationale. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-26 10:39:23 -05:00
russell@unturf.com	99bc6bf014	renamed: docs/CLAUDE.md -> CLAUDE.md	2026-01-26 10:00:07 -05:00

Renamed from docs/CLAUDE.md (Browse further)