This is a utility to turn a MP3 file into a HTML page with a machine generated transcription that looks like this:
While this is still a WIP, please check out usage.md for more details on how to run this end to end.
Supported engines:
- AWS Transcribe -- Sample output
- OpenAI Speech to Text -- Sample output
- Whisper -- Sample output: Tiny, Large models
- Whisper.cpp -- Sample output: Tiny, Large models
- Whisper-Timestamped -- Sample output: Medium model.
- WhisperX -- Sample output: Medium model.