Missing pytorch_model.bin?
#6
by nicholassanders - opened
When downloading via huggingface api with WavLMModel.from_pretrained("speechbrain/emotion-diarization-wavlm-large"), no pytorch_model.bin file is downloaded and an error is raised. I also do not see this file within the files and versions tab. Is the best way to get access to the model through the dropbox link shared on the original Speech_Emotion_Diarization github repo?
Hi @nicholassanders , the model inference is based on speechbrain interface, where .ckpt files are used instead of .bin files. You can try inference code in the model card.
hi!can you do an algoritm to visualize audio with AI?