Large model

[mootje2]

Thanks for the nice afford with this app, I was wondering if I could- use it with the large model because I can see that with the multilanguage the transscription the large model have much better results than the one you are using. I have the large model on my Ubuntu server and test it with Gradio it gives a much better transcription. The question is how to adjust the script the use the large model from my local server?. also I saw in your demo on hugging face there is a microphone I do miss it.
Thanks

[Joshua Lochner]

The purpose of this project is to run whisper directly in your browser, instead of a local server, so, I won't be modifying it to support an external API. However, feel free to clone the repo yourself, then separating the frontend from the backend if you wish to reuse the user interface.

[Yavuz Kömeçoğlu]

Hi @xenova,
We added it to the models list as 'Xenova/whisper-large': [1550]. I download the model, but I get the error "RangeError: offset is out of bounds" during the transcription phase. I get the same error on devices with these different RAMs. How can I operate the Large model?

[midpoint]

whisper-web\src\components\AudioManager.tsx

    const models = {
        // Original checkpoints
        'Xenova/whisper-tiny': [41, 152],
        'Xenova/whisper-base': [77, 291],
        'Xenova/whisper-small': [249],
        'Xenova/whisper-medium': [776],
        'Xenova/whisper-large-v2': [23776],
        'Xenova/whisper-large-v3': [17776],

        // Distil Whisper (English-only)
        'distil-whisper/distil-medium.en': [402],
        'distil-whisper/distil-large-v2': [767],
    };