RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 1, 191, 80]

[Maverick7t]

🐛 Bug

When attempting to train the model using Fairseq, I encountered an error during the training process. Below is the error message:

2024-04-16 15:17:57 | INFO | fairseq.trainer | begin training epoch 1
2024-04-16 15:17:57 | INFO | fairseq_cli.train | Start iterating over samples
Traceback (most recent call last):
File "/home/hp/miniconda3/envs/test_fairseq/bin/fairseq-train", line 8, in
sys.exit(cli_main())
...
...
...
File "/home/hp/miniconda3/envs/test_fairseq/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 310, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/hp/miniconda3/envs/test_fairseq/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 306, 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, 191, 80]