![RDC : accord de Doha, les Congolais entre doute et espoir [Africanews Today]](http://static.euronews.com/articles/stories/09/38/15/81/640x360_cmsv2_2c0586a3-1581-51f0-ba5e-05a4ee4c9cd3-9381581.jpg?1753098215#)
Complete silence is always hallucinated as "ترجمة نانسي قنقر" in Arabic
VAD, probably.
I've only tried the turbo one, but what I can say is that v3 is different from the earlier models.
It looks like it doesn't have the audio descriptions to fall back on and produces hallucinations instead.
The earlier models will also produce some miscellaneous crap when they encounter silence
(they do this regardless of language), but there are more options for how to deal with that.
For example, these things can be effective for the small model (but not for v3):
- the suppress_tokens trick
- setting initial prompt to something like "."
- adjusting logprob_threshold to -0.4 (works for this empty audio, probably not good for general use)
What's Your Reaction?
Like
0
Dislike
0
Love
0
Funny
0
Angry
0
Sad
0
Wow
0
