Whisper should only produce .txt and .vtt files

sul-dlss / speech-to-text

Tools for generating transcript and caption files from media files (e.g. a Docker container for running Whisper on video files in AWS ECS? 🤷🏽)

0 stars 0 forks source link

Closed peetucket closed 1 week ago

peetucket commented 3 weeks ago

Whisper should only produce .txt and .vtt files. Currently it also produces .json, .srt and .tsv. We do not need those extra files.

peetucket commented 1 week ago

No real computation benefit