xenova / whisper-web

ML-powered speech recognition directly in your browser
https://hf.co/spaces/Xenova/whisper-web
MIT License
2.57k stars 274 forks source link

Uncaught (in promise) Error: Unsupported model type: whisper #24

Open Keith-Hon opened 1 year ago

Keith-Hon commented 1 year ago

models.js:3384 Uncaught (in promise) Error: Unsupported model type: whisper at AutoModelForCTC.from_pretrained (models.js:3384:19) at async pipelines.js:2071:33 from_pretrained @ models.js:3384

I finetuned my whisper-small model with peft and then merged it back to the base model.

I then converted it into onnx with

https://github.com/xenova/transformers.js/blob/main/scripts/convert.py

However, when i try to run it with whisper-web, the above error showed up

deeeed commented 3 months ago

I have similar issue using xenova/whisper-medium

abuchnick-aiola commented 2 months ago

Also running into this ... Can this be answered please ? Are we missing some voodoo in order to get it to work ?