Consider supporting SenseVoice in transcription task #53
MaleicAcid
started this conversation in
New Feature
Replies: 1 comment
-
|
The accuracy of the currently released SenseVoice-small is significantly lower than that of Whisper-large-v3, so it will not be considered as a transcription engine for now. I will test SenseVoice-Large after its release. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
SenseVoice released by Alibaba Group claims to be better than the Whisper model in transcription tasks and "requires only 70ms to process 10 seconds of audio, which is 15 times faster than Whisper-Large."
ref@https://github.com/FunAudioLLM/SenseVoice/blob/main/README_zh.md
Beta Was this translation helpful? Give feedback.
All reactions