Can not generate text from local .wav file
#5
by himelbikon - opened
I am trying to generate text from local .wav file. It shows Dimension related problem. But an audio which was generated from amazon polly, only that works well. Other all audios giving this error:
File "C:\Users\Ittest\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 303, in _conv_forward
return F.conv1d(input, weight, bias, self.stride,
RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 58072921, 2]
What mistake am I making? What should I do?
do this : input_values = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt").input_values.squeeze(0)