mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-18 06:10:43 -07:00
James Pine
163528bf69
- Combine engine + model size into one flat dropdown (Qwen3-TTS 1.7B, Qwen3-TTS 0.6B, LuxTTS) in both FloatingGenerateBox and GenerationForm - Add linacodec git dep to requirements.txt (uv-only source, pip can't resolve it from Zipvoice's pyproject.toml) - Remove redundant transitive deps from requirements.txt - Quiet the sidecar setup script (was printing misleading instructions)
36 lines
793 B
Plaintext
36 lines
793 B
Plaintext
# FastAPI and server
|
|
fastapi>=0.109.0
|
|
uvicorn[standard]>=0.27.0
|
|
pydantic>=2.5.0
|
|
|
|
# Database
|
|
sqlalchemy>=2.0.0
|
|
alembic>=1.13.0
|
|
|
|
# ML models
|
|
torch>=2.1.0
|
|
transformers>=4.36.0,<=4.57.6
|
|
accelerate>=0.26.0
|
|
huggingface_hub>=0.20.0
|
|
qwen-tts>=0.0.5
|
|
|
|
# LuxTTS (voice cloning engine)
|
|
# piper-phonemize needs custom index (no PyPI wheels)
|
|
--find-links https://k2-fsa.github.io/icefall/piper_phonemize.html
|
|
# linacodec is a git-only dep of Zipvoice (uv-only source, pip can't resolve it)
|
|
linacodec @ git+https://github.com/ysharma3501/LinaCodec.git
|
|
Zipvoice @ git+https://github.com/ysharma3501/LuxTTS.git
|
|
|
|
# Audio processing
|
|
librosa>=0.10.0
|
|
soundfile>=0.12.0
|
|
numpy>=1.24.0
|
|
numba>=0.60.0,<0.61.0
|
|
|
|
# HTTP client (for CUDA backend download)
|
|
httpx>=0.27.0
|
|
|
|
# Utilities
|
|
python-multipart>=0.0.6
|
|
Pillow>=10.0.0
|