Using a .pt file as the audio_model

#5
by AniBirage - opened

image.png

Hi, I'm trying to integrate the wav2vec model as the audio_model of the following image, when I click on Download, it downloadas .pt file
How do I integrate the .pt file/model and use it in release_config.yaml file

You can find converters here:

https://github.com/huggingface/transformers/blob/main/src/transformers/models/wav2vec2/convert_wav2vec2_original_pytorch_checkpoint_to_pytorch.py

I looked into it, I'm getting errors; do you know how to run the script or any specific instructions which I might have missed?

Sign up or log in to comment