support for huggingface wav2vec XLSR ?

Question

support for huggingface wav2vec XLSR ?

StephennFernandes opened this issue 3 years ago · 3 comments

Hey does bertviz support visualization for wav2vec XLSR ASR models from huggingface ? where one end is a spectrogram and the other is corresponding transcriptions with attention visualizations of the corresponding text that the audio

Answer 1 · 2021-12-04T01:34:40.000Z

Hi @StephennFernandes, thanks for the question! Unfortunately bertviz only supports fully text-based models. Nice idea though.
Best,
Jesse

Answer 2 · 2021-12-10T09:28:48.000Z

@jessevig do you know of any other alternatives that i can use to visualize the attention in wav2vec2 ASR models ? any leads you provide would really mean a lot

Answer 3 · 2021-12-11T00:30:54.000Z

Sorry @StephennFernandes I don't have any great suggestions there.