Generate subtitles (.srt and .vtt) from audio files using OpenAI's Whisper models.
Using faster-whisper, a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models.
This is a fork of m1guelpf/whisper-subtitles with added support for VAD, selecting a language, use the language specific models and download the .vtt/.srt files directly from the result.
You can run the model on Replicate.
First, download the pre-trained weights:
cog run script/download-weights
Then, you can run predictions:
cog predict -i audio_path=@/path/to/audio.mp3
Or, build a Docker image:
cog build
Or, push it to Replicate:
cog push r8.im/...