add new model to use

[lewdon]

I want to add new model as ASR_MODEL=base ,but I try to download the Belle-distilwhisper-large-v2 to the Model Path.But it can't run rightly ?

[lewdon]

Any update?

[cmccullough14]

I actually have the same issue, I would prefer to use the "medium" model but when I use either of the following commands the webserver won't even open for me once the container starts.

1. docker run -d --net whispernetwork --name project_openai_whisper_asr_webservice -h whisperai -p 9000:9000 -e ASR_MODEL=medium -e ASR_ENGINE=openai_whisper -it onerahmet/openai-whisper-asr-webservice:latest
2. docker run -d --net whispernetwork --name project_openai_whisper_asr_webservice -h whisperai -p 9000:9000 -e ASR_MODEL=small -e ASR_ENGINE=openai_whisper -it onerahmet/openai-whisper-asr-webservice:latest

However running this command does work and the webserver starts immediately:

1. docker run -d --net whispernetwork --name project_openai_whisper_asr_webservice -h whisperai -p 8080:9000 -e ASR_MODEL=base -e ASR_ENGINE=openai_whisper -it onerahmet/openai-whisper-asr-webservice:latest

What I'd love to see would be a model-switcher so I can save whichever model(s) I want to use and then select it in the UI or specify the model to use in the endpoint

[almarax]

same here, it doesn't work: ASR_MODEL=large-v3

docker command: docker run -d --gpus all -p 9000:9000 -e ASR_MODEL=large-v3 -e ASR_ENGINE=openai_whisper onerahmet/openai-whisper-asr-webservice:latest-gpu

docker log output: RuntimeError: Model large-v3 not found; available models = ['tiny.en', 'tiny', 'base.en', 'base', 'small.en', 'small', 'medium.en', 'medium', 'large-v1', 'large-v2', 'large']

[lewdon]

any update ？

[wheynelau]

@lewdon I will try to take a look at this, just chanced on this repo