Open guijuzhejiang opened 2 years ago
not sure if this answer your question,
I create a new model by using "create_wav2vec2.py" by changing https://github.com/pytorch/android-demo-app/blob/master/SpeechRecognition/create_wav2vec2.py
model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
to
other model, for example ,my own model that i retrieved from huggingface
model1 = Wav2Vec2ForCTC.from_pretrained("mictiong85/wav2vec2-base-timit-demo-colab")
Nevertheless, I am facing other error
The wav2vec2 used in the SpeechRecognition example does not have a language model. How to add language model in the demo app?