freddyaboulton/omni-mini-webrtc · how to change whisper small to large?

while change load_model in inference.py, the model fail. to infer
here is the output:

File "/home/xxx/work/omni-mini-webrtc/litgpt/model.py", line 465, in forward
x_fc_1 = self.fc_1(x)
File "/home/xxx/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/xxx/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
return forward_call(*args, **kwargs)
File "/home/xxx/.local/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 125, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 shapes cannot be multiplied (196x1280 and 768x4864)

I try to modify config.py but fail to fix