mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-20 15:20:39 -07:00
James Pine
f77dd621e2
Integrate Alibaba's CosyVoice2-0.5B and Fun-CosyVoice3-0.5B as a new TTS engine supporting 9 languages, zero-shot voice cloning, and instruct control (emotions, speed, volume, dialects). The CosyVoice source is cloned at setup time into backend/vendors/ since no PyPI package exists. A modelscope→HuggingFace shim redirects model downloads to the public HF repos, and a lightweight pylogger shim avoids pulling in pytorch-lightning as a transitive dependency. Backend: cosyvoice_backend.py, __init__.py registry, models.py regex Frontend: engine selector, language map, Zod schema, model descriptions Infra: requirements.txt, justfile, release.yml, Dockerfile, PyInstaller
65 lines
1.6 KiB
Plaintext
65 lines
1.6 KiB
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
|
|
|
|
# Chatterbox TTS sub-dependencies (chatterbox-tts itself is installed
|
|
# --no-deps in the setup script because it pins numpy<1.26 / torch==2.6
|
|
# which are incompatible with Python 3.12+)
|
|
conformer>=0.3.2
|
|
diffusers>=0.29.0
|
|
omegaconf
|
|
pykakasi
|
|
resemble-perth>=1.0.1
|
|
s3tokenizer
|
|
spacy-pkuseg
|
|
pyloudnorm
|
|
|
|
# HumeAI TADA sub-dependencies (hume-tada itself is installed
|
|
# --no-deps in the setup script because it pins torch>=2.7,<2.8.
|
|
# descript-audio-codec is NOT installed — it pulls onnx/tensorboard
|
|
# via descript-audiotools. A lightweight shim in utils/dac_shim.py
|
|
# provides the only class TADA uses: Snake1d.)
|
|
torchaudio
|
|
|
|
# CosyVoice2/3 sub-dependencies (the cosyvoice source is cloned at
|
|
# setup time into backend/vendors/CosyVoice — no PyPI package exists)
|
|
hyperpyyaml>=1.2.0
|
|
onnxruntime>=1.18.0
|
|
openai-whisper>=20231117
|
|
tiktoken
|
|
einops
|
|
inflect
|
|
|
|
# Audio processing
|
|
librosa>=0.10.0
|
|
soundfile>=0.12.0
|
|
numpy>=1.24.0
|
|
numba>=0.60.0,<0.61.0
|
|
pedalboard>=0.9.0
|
|
|
|
# HTTP client (for CUDA backend download)
|
|
httpx>=0.27.0
|
|
|
|
# Utilities
|
|
python-multipart>=0.0.6
|
|
Pillow>=10.0.0
|