sasikr2
/

whisper-large-v3-turbo-ct2

Automatic Speech Recognition

Model card Files Files and versions Community

sasikr2 commited on 25 days ago

Commit

9b641a0

•

1 Parent(s): b11565d

Update README.md

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -6,7 +6,9 @@ pipeline_tag: automatic-speech-recognition
 ---
 # Whisper Ctranslate2
 Whisper large-v3-turbo is distilled version of large-v3, only difference is number of decoder layers.
-In turbo, there are only 4 decoder layers instead of 32 in large-v3
 This repo contains the conversion of [whisper-large-v3-turbo openai checkpoint](https://github.com/openai/whisper) to [ctranslate2](https://github.com/OpenNMT/CTranslate2) format.
 Command to convert safetensors to ctranslate format checkpoint :

 ---
 # Whisper Ctranslate2
 Whisper large-v3-turbo is distilled version of large-v3, only difference is number of decoder layers.
+In turbo, there are only 4 decoder layers instead of 32 in large-v3.
 This repo contains the conversion of [whisper-large-v3-turbo openai checkpoint](https://github.com/openai/whisper) to [ctranslate2](https://github.com/OpenNMT/CTranslate2) format.
 Command to convert safetensors to ctranslate format checkpoint :