-
|
I used whisper with a large model. I run it 3 times and get 3 results. japaneseV2.1.mp4 |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
|
Whisper is not very accurate on singing voices in general. By using the |
Beta Was this translation helpful? Give feedback.
Whisper is not very accurate on singing voices in general. By using the
largemodel and giving a prompt (of the words preceding the audio), it gets pretty close, except the last line where it hallucinated and got the timestamp wrong.