search

p0p4k / vits2_pytorch

unofficial vits2-TTS implementation in pytorch
https://arxiv.org/abs/2307.16430
MIT License
465 stars 81 forks source link

hop size issue #78

Open Paintako opened 5 months ago

Paintako commented 5 months ago

Hello,

When I train using a custom dataset, I encounter the following error with the following parameters:

"filter_length": 2048, "hop_length": 512, "win_length": 2048,

File "/mnt/Linux_DATA/synthesis/model/vits2_pytorch/train_ms.py", line 441, in train_and_evaluate loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel File "/home/p76111652/.conda/envs/vits/lib/python3.8/site-packages/torch/nn/functional.py", line 3263, in l1_loss expanded_input, expanded_target = torch.broadcast_tensors(input, target) File "/home/p76111652/.conda/envs/vits/lib/python3.8/site-packages/torch/functional.py", line 74, in broadcast_tensors return _VF.broadcast_tensors(tensors) # type: ignore[attr-defined] RuntimeError: The size of tensor a (16) must match the size of tensor b (8) at non-singleton dimension 2

It seems that the shape of y_mel does not match the shape of y_hat_mel when the hop_size is increased beyond 256. Any help would be extremely helpful, thanks!

lexkoro commented 4 months ago

@Paintako You also need to change the segment_size in config.