MCPcopy Index your code
hub / github.com/AIFSH/ComfyUI-WhisperX

github.com/AIFSH/ComfyUI-WhisperX @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
121 symbols 337 edges 16 files 20 documented · 17% ● updated 15mo ago★ 6210 open issues
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

ComfyUI-WhisperX

a comfyui cuatom node for audio subtitling based on whisperX and translators

webpage
## Features - export `srt` file for subtitle was supported - translate was supported by [translators](https://github.com/UlionTse/translators) with huge number engine - mutiple speaker diarization was supported by [pyannote-audio](https://github.com/pyannote/pyannote-audio) - huge comfyui custom nodes can merge in whisperx ## How to use make sure `ffmpeg` is worked in your commandline for Linux 
apt update
apt install ffmpeg
for Windows,you can install `ffmpeg` by [WingetUI](https://github.com/marticliment/WingetUI) automatically then! 
git clone https://github.com/AIFSH/ComfyUI-WhisperX.git
cd ComfyUI-WhisperX
pip install -r requirements.txt
`weights` will be downloaded from huggingface automatically! if you in china,make sure your internet attach the huggingface or if you still struggle with huggingface, you may try follow [hf-mirror](https://hf-mirror.com/) to config your env. to speaker diarization, you need! 1. Accept [`pyannote/segmentation-3.0`](https://hf.co/pyannote/segmentation-3.0) user conditions 2. Accept [`pyannote/speaker-diarization-3.1`](https://hf.co/pyannote/speaker-diarization-3.1) user conditions 3. Create access token at [`hf.co/settings/tokens`](https://hf.co/settings/tokens). ## Tutorial [Demo](https://www.bilibili.com/video/BV19i421y7jb/) ## WeChat Group && Donate
Wechat donate
## Thanks - [whisperX](https://github.com/m-bain/whisperX.git) - [translators](https://github.com/UlionTse/translators)

Core symbols most depended-on inside this repo

format_timestamp
called by 6
whisperx/utils.py
encode
called by 5
whisperx/asr.py
apply
called by 5
whisperx/vad.py
load_audio
called by 5
whisperx/audio.py
exact_div
called by 3
whisperx/utils.py
previewAudio
called by 3
web/js/uploadAudio.js
read
called by 2
nodes.py
transcribe
called by 2
whisperx/asr.py

Shape

Method 49
Function 45
Class 27

Languages

Python88%
TypeScript12%

Modules by API surface

whisperx/utils.py30 symbols
whisperx/asr.py17 symbols
nodes.py12 symbols
whisperx/alignment.py10 symbols
whisperx/SubtitlesProcessor.py10 symbols
whisperx/vad.py9 symbols
web/js/uploadAudio.js7 symbols
web/js/previewSRT.js7 symbols
whisperx/types.py6 symbols
whisperx/diarize.py6 symbols
whisperx/audio.py4 symbols
whisperx/conjunctions.py2 symbols

For agents

$ claude mcp add ComfyUI-WhisperX \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact