v3ucn / Modelscope_Faster_Whisper_Multi_Subtitle

基于Faster-whisper和modelscope一键生成双语字幕,双语字幕生成器,基于离线大模型,Generate bilingual subtitles with one click based on Faster-whisper and modelscope. Off-line large model
MIT License
288 stars 30 forks source link

Modelscope_Faster_Whisper_Multi_Subtitle

基于Faster-whisper和modelscope一键生成双语字幕,双语字幕生成器,基于离线大模型

Generate bilingual subtitles with one click based on Faster-whisper and modelscope. Off-line large model




Quick Install with Conda

conda create -n venv python=3.9
conda activate venv

Install Manually

Make sure you have the distutils for python3 installed

sudo apt-get install python3.9-distutils

Pip Packages

pip install -r requirements.txt

pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 

FFmpeg

Conda Users
conda install ffmpeg
Ubuntu/Debian Users
sudo apt install ffmpeg
sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
MacOS Users
brew install ffmpeg
Windows Users
winget install ffmpeg

or

choco install ffmpeg

下载 whisper-large-v3-turbo

python3 download_model.py

基于 Ollama 的对话式大模型翻译

ollama run qwen2:7b
ollama serve

how to use

python3 app.py

目前支持双语字幕类型:中英、英中、日中、韩中

avatar

Credits

Special thanks to the following projects and contributors: