Sreyan Ghosh

``` File "train.py", line 25, in trainer.train() File "/speech/sreyan/slt/data2vec-pytorch/audio/trainer.py", line 140, in train train_loss = self.train_epoch(epoch) File "/speech/sreyan/slt/data2vec-pytorch/audio/trainer.py", line 105, in train_epoch loss = self.train_step(batch) File "/speech/sreyan/slt/data2vec-pytorch/audio/trainer.py", line 66, in...

You can try running : `python train.py --config audio/configs/wav2vec2-pretraining.yaml` to reproduce.

Hi, Sorry for the delay, I will post it today, was busy with conference deadlines. @arxyzan can you please re-open this?

I had to export this for my env: `export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib/`

Same here, anyway to fix this?

I face the same problem!

``` roped = (x * cos) + (rotated * sin) RuntimeError: The size of tensor a (128) must match the size of tensor b (64) at non-singleton dimension 3 ```

I get the same error! Has anyone found out a solution to this? Thanks!