engineering/uncloseai-speech
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Make Qwen3-TTS the default engine, add CPU-only docker support

Browse source 
- 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
This commit is contained in:
russell@unturf.com 2026-01-26 10:40:29 -05:00
parent 4a019cf897
commit b315659be6
9 changed files with 572 additions and 951 deletions
Download patch file Download diff file Expand all files Collapse all files

2
Dockerfile
View file

@ -1,4 +1,4 @@
FROM python:3.11-slim
FROM python:3.12-slim
RUN --mount=type=cache,target=/root/.cache/pip pip install -U pip