Issue with large-v3

[jwvid]

Which OS are you using?

• OS: [e.g. iOS or Windows.. If you are using Google Colab, just Colab.]
  Windows 10 (nvidia gpu)

When I select the 'large-v3' model and press the generate button, the following message is displayed, and the process does not continue.

Error transcribing file on line Invalid model size 'large-v3', expected one of: tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2, large C:\Whisper-WebUI\venv\lib\site-packages\torch\cuda\memory.py:329: FutureWarning: torch.cuda.reset_max_memory_allocated now calls torch.cuda.reset_peak_memory_stats, which resets /all/ peak memory stats. warnings.warn(

[jhj0517]

large-v3 cannot currently be used in faster-whisper.
If you want to use large-v3, set DISABLE_FASTER_WHISPER to true in user-start-webui.bat file as it uses the OpenAI whisper implementation.

There is an ongoing issue with :

• faster-whisper #544

[jurandfantom]

large-v3 cannot currently be used in faster-whisper. If you want to use large-v3, set DISABLE_FASTER_WHISPER to true in user-start-webui.bat file as it uses the OpenAI whisper implementation.

There is an ongoing issue with :

* [faster-whisper #544](https://github.com/guillaumekln/faster-whisper/issues/544)

Thanks for explanation. Sadly I get error and not sure exactly why is that. If I can provide any additional informations/errors, please point me out where look for those.

CMD log:

To create a public link, set share=True in launch().
Error transcribing file: [WinError 2] The system cannot find the file specified
E:\Magazyn\Grafika\AI\Pinokio\api\whisper-webui.pinokio.git\app\venv\lib\site-packages\torch\cuda\memory.py:329: FutureWarning: torch.cuda.reset_max_memory_allocated now calls torch.cuda.reset_peak_memory_stats, which resets /all/ peak memory stats.
warnings.warn(

[inRm3D]

SYSTRAN/faster-whisper#578

seems now support v3

[jhj0517]

That's right! faster-whisper now supports large-v3, so I'm closing this!