Closed Tps-F closed 1 month ago
That works for you? Because even with your pull request in my case training in 44k doesn't work
I know and I'm sorry I forgot to convert it to the draft. I'm just helping Blaise for now-
loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
Process Process-1:
Traceback (most recent call last):
File "C:\Users\X\Downloads\Applio\env\lib\multiprocessing\process.py", line 315, in _bootstrap
self.run()
File "C:\Users\X\Downloads\Applio\env\lib\multiprocessing\process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "C:\Users\X\Downloads\Applio\rvc\train\train.py", line 258, in run
train_and_evaluate(
File "C:\Users\X\Downloads\Applio\rvc\train\train.py", line 465, in train_and_evaluate
loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
File "C:\Users\X\Downloads\Applio\env\lib\site-packages\torch\nn\functional.py", line 3297, in l1_loss
expanded_input, expanded_target = torch.broadcast_tensors(input, target)
File "C:\Users\X\Downloads\Applio\env\lib\site-packages\torch\functional.py", line 73, in broadcast_tensors
return _VF.broadcast_tensors(tensors) # type: ignore[attr-defined]
RuntimeError: The size of tensor a (23) must match the size of tensor b (13) at non-singleton dimension 2
Issue: #428