雾聪
2024-04-19 1d6cb3bba47fb3139379541598bfdbc4c985dfda
setup.py
@@ -10,44 +10,42 @@
requirements = {
    "install": [
        "setuptools>=38.5.1",
        "humanfriendly",
        "scipy>=1.4.1",
        "librosa",
        "jamo",  # For kss
        "PyYAML>=5.1.2",
        "soundfile>=0.12.1",
        "h5py>=2.10.0",
        # "soundfile>=0.12.1",
        "kaldiio>=2.17.0",
        "kaldi-io==0.9.8",
        "torch_complex",
        "nltk>=3.4.5",
        "onnxruntime",
        "numexpr",
        # "nltk>=3.4.5",
        # ASR
        "sentencepiece",
        "sentencepiece", # train
        "jieba",
        "rotary_embedding_torch",
        # "rotary_embedding_torch",
        # "ffmpeg-python",
        # TTS
        "pypinyin>=0.44.0",
        "espnet_tts_frontend",
        # "pypinyin>=0.44.0",
        # "espnet_tts_frontend",
        # ENH
        "pytorch_wpe",
        "editdistance>=0.5.2",
        "tensorboard",
        "g2p",
        "nara_wpe",
        "Cython",
        # "g2p",
        # "nara_wpe",
        # PAI
        "oss2",
        "edit-distance",
        "textgrid",
        "protobuf",
        # "edit-distance",
        # "textgrid",
        # "protobuf",
        "tqdm",
        "umap_learn",
        "jaconv",
        "hydra-core>=1.3.2",
        "tensorboardX",
        "rotary_embedding_torch",
    ],
    # train: The modules invoked when training only.
    "train": [
        "editdistance",
        "wandb",
    ],
    # all: The modules should be optionally installled due to some reason.
    #      Please consider moving them to "install" occasionally
@@ -85,6 +83,17 @@
        "sphinx-markdown-tables>=0.0.12",
        "configargparse>=1.2.1"
    ],
    "llm":[
        "transformers>=4.32.0",
        "accelerate",
        "tiktoken",
        "einops",
        "transformers_stream_generator>=0.0.4",
        "scipy",
        "torchvision",
        "pillow",
        "matplotlib",
    ],
}
requirements["all"].extend(requirements["train"])
requirements["test"].extend(requirements["train"])
@@ -104,7 +113,7 @@
    name="funasr",
    version=version,
    url="https://github.com/alibaba-damo-academy/FunASR.git",
    author="Speech Lab of DAMO Academy, Alibaba Group",
    author="Speech Lab of Alibaba Group",
    author_email="funasr@list.alibaba-inc.com",
    description="FunASR: A Fundamental End-to-End Speech Recognition Toolkit",
    long_description=open(os.path.join(dirname, "README.md"), encoding="utf-8").read(),
@@ -129,4 +138,8 @@
        "License :: OSI Approved :: Apache Software License",
        "Topic :: Software Development :: Libraries :: Python Modules",
    ],
    entry_points={"console_scripts": [
        "funasr = funasr.bin.inference:main_hydra",
        "funasr-export = funasr.bin.export:main_hydra",
    ]},
)