search

pytorch / android-demo-app

PyTorch android examples of usage in applications
1.46k stars 604 forks source link

[Speech Recognition] Using pretrained model other than Wav2Vec2 #226

Open mictiong85 opened 2 years ago

mictiong85 commented 2 years ago

I am novice here and I am using different pretrained model other than Wav2Vec2. I load the pretrained model from hugging face , but during the sanity check , the text is totally wrong.

Could somebody advise what is wrong here?

From image to

image

The original wav2vec model texts image but i got this for the other pretrained model i uploaded from huggging face image

StephennFernandes commented 2 years ago

Hey I've been facing the same issue, were you able to find a fix for the same ???