Transcribe video and audio files with OpenAI's speech recoginition model Whisper

• Clone this repository
• Install the requirements pip install -r requirements.txt Note:, if you're using the portable version of ComfyUI you'll have to run against the environments python: path\to\ComfyUI\python_embeded\python.exe -m pip install -r requirements.txt
• Restart ComfyUI if running, and refresh any active tabs.

Load a OpenAI Whisper model

Transcribe with transformers

Transcribe with openai on Whisper V2 model. Requires a OpenAI access token.

Refer to Salt AI Documentation for node information.