[project] name = "fish-speech" version = "0.1.0" authors = [ {name = "Lengyue", email = "lengyue@lengyue.me"}, ] description = "Fish Speech" readme = "README.md" requires-python = ">=3.10" keywords = ["TTS", "Speech"] license = {text = "CC BY-NC-SA 4.0"} classifiers = [ "Programming Language :: Python :: 3", ] dependencies = [ "numpy<=1.26.4", "transformers>=4.45.2", "datasets==2.18.0", "lightning>=2.1.0", "hydra-core>=1.3.2", "tensorboard>=2.14.1", "natsort>=8.4.0", "einops>=0.7.0", "librosa>=0.10.1", "rich>=13.5.3", "gradio>5.0.0", "wandb>=0.15.11", "grpcio>=1.58.0", "kui>=1.6.0", "uvicorn>=0.30.0", "loguru>=0.6.0", "loralib>=0.1.2", "pyrootutils>=1.0.4", "vector_quantize_pytorch==1.14.24", "resampy>=0.4.3", "einx[torch]==0.2.2", "zstandard>=0.22.0", "pydub", "pyaudio", "faster_whisper", "modelscope==1.17.1", "funasr==1.1.5", "opencc-python-reimplemented==0.1.7", "silero-vad", "ormsgpack", "tiktoken>=0.8.0", "pydantic==2.9.2", "cachetools", ] [project.optional-dependencies] stable = [ "torch<=2.4.1", "torchaudio", ] [build-system] requires = ["setuptools", "setuptools-scm"] build-backend = "setuptools.build_meta" [tool.setuptools] packages = ["fish_speech", "tools"]