Purfview
Purfview
> I think this bug can trigger the hallucinations loop because on some hallucination it wouldn't trigger the prompt reset on high temperature , because higher temperatures are not computed...
Another example of hallucination fix: https://github.com/openai/whisper/discussions/1962
> Could not load library libcudnn_ops_infer.so.8 You can find cuBLAS and cuDNN libs for Linux there at Releases -> https://github.com/Purfview/whisper-standalone-win Not tested, report if they work.
> Large-v3 model hallucinates, large-v2 doesn't It's known that large-v3 hallucinates much more than large-v2, read there: [Whisper-v3 Hallucinations on Real World Data](https://deepgram.com/learn/whisper-v3-results)
> Then I guess I'll stay with large-v3. Did you meant "large-v2"? On my Standalone Faster-Whisper I've added auto-offsets to whisper's pseudo-vad thresholds when "v3" is in use, you can...
> does it yield better result than large-v2 using your parameters with large-v3? You tell me, as I don't use large-v3. IMO large-v2 is better.
> Actually, I believe I can get the original transcript even if I use the "translate" task, but how? Is that possible? Not possible.
What is your GPU model?
Make sure you are using the last faster-whisper version. Check what PyAV version is there too.
Try to downgrade it, I don't have other ideas... `pip install --force-reinstall av==11.0.0`