Nilaier

I benchmarked the models on my laptop using the same audio file in both **sequential** and **batched** processing. Seems that `large-v3-turbo` generally performs exceptionally well, offering greater accuracy than the...

> Just chiming in, I've tried using v3-turbo for streaming and found that it hallucinates more/misses audio more than other faster-whisper models. For example for this 10 second audio clip...

> > > Just chiming in, I've tried using v3-turbo for streaming and found that it hallucinates more/misses audio more than other faster-whisper models. For example for this 10 second...