Haitao comments

Repositories
Issues
Comments

Results 4 comments of


                                            Haitao

convert squeezewave model to pytorch script for C++ inference.

> > > You might try to use the script used to convert torch to onnx provided for WaveGlow, I tried before but fail to convert the onnx to caffe2....

whisper model's default task should be "transcribe"

Thank you for your explanation.

whisper identified the wrong language

If you use pipeline, you should add option like generate_kwargs = {"task":"transcribe", "language":""} ref1: https://colab.research.google.com/drive/1rS1L4YSJqKUH_3YxIQHBI982zso23wor#scrollTo=dPD20IkEDsbG ref2: https://github.com/huggingface/transformers/issues/22331 however, I think default task should be "transcribe" not "translate". I insist It's...

whisper identified the wrong language

maybe you can checked your fine-tuned model's config.json or generation_config.json, double check the default task type, I think it's null or "transcribe"