Updating fast-whisper to 1.0.2 for distil-large-V3 support

[reversed95]

As per the title, an update to support the newer models would be great. Thanks for the work anyway.

[debjit]

+1

[flefevre]

Here: https://huggingface.co/distil-whisper/distil-large-v2
They said there is no change in the architecture from v2 to v3
but with improve performance:

The result is a distilled model that performs to within 1% WER of large-v3 on long-form audio using both the sequential and chunked algorithms, and outperforms distil-large-v2 by 4.8% using the sequential algorithm. The model is also faster than previous Distil-Whisper models: 6.3x faster than large-v3, and 1.1x faster than distil-large-v2.

Update: following the release of OpenAI's Whisper large-v3, an updated distil-large-v3 model was published. This distil-large-v3 model surpasses the performance of the distil-large-v2 model, with no architecture changes and better support for sequential long-form generation. Thus, it is recommended that the distil-large-v3 model is used in-place of the large-v2 model.

perhaps it is very simple to add distil-large-v3 ?

[flefevre]

I have tested both configuration distil-large-v2 and distil-large-v3.
It seems to be compatible BUT when I upload an audio in french it returns me both v2 and v3 in english and not in french even if i select the language fr in the webservice interface.
strange...