├── docker-compose.yml ├── download_model.py ├── LICENSE ├── api.py ├── Dockerfile ├── README.md └── .gitignore /docker-compose.yml: -------------------------------------------------------------------------------- 1 | services: 2 | cosyvoice_server: 3 | image: cosyvoice 4 | container_name: cosyvoice_server 5 | ports: 6 | - "8080:8080" 7 | restart: always 8 | runtime: nvidia 9 | environment: 10 | NVIDIA_DRIVER_CAPABILITIES: all 11 | NVIDIA_VISIBLE_DEVICES: all -------------------------------------------------------------------------------- /download_model.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | # -*- encoding: utf-8 -*- 3 | 4 | from modelscope import snapshot_download 5 | 6 | snapshot_download('iic/CosyVoice-300M', local_dir='pretrained_models/CosyVoice-300M') 7 | snapshot_download('iic/CosyVoice-300M-SFT', local_dir='pretrained_models/CosyVoice-300M-SFT') 8 | snapshot_download('iic/CosyVoice-300M-Instruct', local_dir='pretrained_models/CosyVoice-300M-Instruct') 9 | snapshot_download('iic/CosyVoice-ttsfrd', local_dir='pretrained_models/CosyVoice-ttsfrd') -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2024 小武Alan 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /api.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | # -*- encoding: utf-8 -*- 3 | 4 | from fastapi import FastAPI, Form 5 | import os 6 | import uuid 7 | from fastapi.responses import StreamingResponse 8 | from cosyvoice.cli.cosyvoice import CosyVoice 9 | from cosyvoice.utils.file_utils import load_wav 10 | import torchaudio 11 | from io import BytesIO 12 | 13 | cosyvoice = CosyVoice('pretrained_models/CosyVoice-300M-SFT') 14 | print(cosyvoice.list_avaliable_spks()) 15 | app = FastAPI() 16 | 17 | # Text to Speech (TTS) API 18 | @app.post("/v1/tts") 19 | async def tts( 20 | text: str = Form(None), 21 | spk: str = Form("中文女"), 22 | ): 23 | audio_buffer = BytesIO() 24 | for output in cosyvoice.inference_sft(text, spk, stream=False): 25 | torchaudio.save(audio_buffer, output['tts_speech'], 22050, format="wav") 26 | audio_buffer.seek(0) 27 | 28 | return StreamingResponse(audio_buffer, media_type="audio/wav", headers={"Content-Disposition": "attachment; filename=output.wav"}) 29 | 30 | if __name__ == "__main__": 31 | api_port = os.getenv("API_PORT", 8080) 32 | api_host = os.getenv("API_HOST", "127.0.0.1") 33 | import uvicorn 34 | uvicorn.run(app, host=api_host, port=int(api_port)) 35 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM nvidia/cuda:12.3.2-cudnn9-runtime-ubuntu22.04 AS base 2 | RUN apt-get update && apt-get install -y \ 3 | ffmpeg \ 4 | tar \ 5 | wget \ 6 | git \ 7 | bash \ 8 | vim 9 | 10 | # Install Miniconda 11 | RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh \ 12 | && mkdir /root/.conda \ 13 | && bash Miniconda3-latest-Linux-x86_64.sh -b \ 14 | && rm -f Miniconda3-latest-Linux-x86_64.sh 15 | ENV PATH="/root/miniconda3/bin:${PATH}" 16 | 17 | # Install requirements 18 | RUN conda config --add channels conda-forge && \ 19 | conda config --set channel_priority strict 20 | RUN conda create -y -n cosyvoice python=3.8 21 | ENV CONDA_DEFAULT_ENV=cosyvoice 22 | ENV PATH="/root/miniconda3/bin:/opt/conda/envs/cosyvoice/bin:${PATH}" 23 | RUN git clone https://github.com/FunAudioLLM/CosyVoice.git /root/CosyVoice 24 | WORKDIR /root/CosyVoice 25 | RUN git submodule update --init --recursive 26 | RUN pip install -r requirements.txt 27 | 28 | # Set environment variables 29 | ENV PYTHONPATH=third_party/Matcha-TTS 30 | ENV API_HOST=0.0.0.0 31 | ENV API_PORT=8080 32 | 33 | # Run 34 | COPY download_model.py . 35 | RUN python download_model.py 36 | COPY api.py . 37 | CMD ["python", "api.py"] -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # CosyVoiceDocker 2 | 3 | This repository provides a Docker image for [CosyVoice](https://github.com/FunAudioLLM/CosyVoice), enabling you to deploy the CosyVoice ASR service within a Docker container. 4 | 5 | ## Usage 6 | 7 | To run this Docker container, you’ll need a machine with NVIDIA GPU support and the NVIDIA Container Toolkit installed. For detailed installation steps, please refer to the [NVIDIA Container Toolkit](https://notes.xiaowu.ai/%E5%BC%80%E5%8F%91%E7%AC%94%E8%AE%B0/AI/NVIDIA#%E5%AE%89%E8%A3%85+NVIDIA+Container+Toolkit) guide. 8 | 9 | ### Build the Docker image 10 | 11 | ```shell 12 | $ docker build -t cosyvoice . 13 | ``` 14 | 15 | ### Using docker command 16 | 17 | ```shell 18 | $ docker run -d --name cosyvoice_server -p 8080:8080 \ 19 | --runtime=nvidia \ 20 | -e NVIDIA_DRIVER_CAPABILITIES=all \ 21 | -e NVIDIA_VISIBLE_DEVICES=all \ 22 | cosyvoice 23 | ``` 24 | 25 | ### Using docker compose 26 | 27 | 1. Create a `docker-compose.yml` file: 28 | ```yaml 29 | services: 30 | cosyvoice_server: 31 | image: cosyvoice 32 | container_name: cosyvoice_server 33 | ports: 34 | - "8080:8080" 35 | restart: always 36 | runtime: nvidia 37 | environment: 38 | NVIDIA_DRIVER_CAPABILITIES: all 39 | NVIDIA_VISIBLE_DEVICES: all 40 | ``` 41 | 2. Start the container: 42 | ```shell 43 | $ docker compose up -d 44 | ``` 45 | 46 | ## Testing 47 | 48 | To test the API, use `curl`: 49 | 50 | ```shell 51 | curl -X POST \ 52 | "http://127.0.0.1:8080/v1/tts" \ 53 | -F "text=你好，欢迎使用语音合成服务" \ 54 | -F "spk=中文女" \ 55 | --output output.wav 56 | ``` -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/latest/usage/project/#working-with-version-control 110 | .pdm.toml 111 | .pdm-python 112 | .pdm-build/ 113 | 114 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 115 | __pypackages__/ 116 | 117 | # Celery stuff 118 | celerybeat-schedule 119 | celerybeat.pid 120 | 121 | # SageMath parsed files 122 | *.sage.py 123 | 124 | # Environments 125 | .env 126 | .venv 127 | env/ 128 | venv/ 129 | ENV/ 130 | env.bak/ 131 | venv.bak/ 132 | 133 | # Spyder project settings 134 | .spyderproject 135 | .spyproject 136 | 137 | # Rope project settings 138 | .ropeproject 139 | 140 | # mkdocs documentation 141 | /site 142 | 143 | # mypy 144 | .mypy_cache/ 145 | .dmypy.json 146 | dmypy.json 147 | 148 | # Pyre type checker 149 | .pyre/ 150 | 151 | # pytype static type analyzer 152 | .pytype/ 153 | 154 | # Cython debug symbols 155 | cython_debug/ 156 | 157 | # PyCharm 158 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 159 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 160 | # and can be added to the global gitignore or merged into this file. For a more nuclear 161 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 162 | #.idea/ 163 | --------------------------------------------------------------------------------