Offline example

[sausax]

Can somebody provide and example of how to run this with model file locally present ? I am planning to run it on machine that does not have internet access.

[jpc]

Hey, you need to download all the models manually and everything else should work. Here is an example that pulls the models into a Docker image:

https://github.com/collabora/WhisperFusion/blob/c58a8d1446a768833811aca9dbdfb6388957fdcb/docker/scripts/setup-whisperfusion.sh#L19-L23

[julienreszka]

@sausax Hi, have you managed to do a full example?

Whisper is so easy to use

model = whisper.load_model("base")
result = model.transcribe(audio_file)

Is there any way we can have something like that with WhisperSpeech?

I'm a bit confused by the docker/scripts/setup-whisperfusion.sh

[BBC-Esq]

You can check out the examples folder.