SubZtep's picture
Upload optimized int8 whisper turbo model
1fb44df
|
Raw
History Blame Contribute Delete
295 Bytes
metadata
tags:
  - automatic-speech-recognition
  - whisper
  - ctranslate2
  - faster-whisper
  - audio
language:
  - hu

whisper-large-v3-turbo-hu-ct2-int8

This is a CTranslate2 / faster-whisper converted version of openai/whisper-large-v3-turbo quantized to int8. Optimized for fast CPU inference.