n_speakers > 0 有问题啊兄弟

[wlz987]

n_speakers > 0 has problem

[daniilrobnikov]

Hi @longzewei ! Thanks for addressing the issue.
Can you elaborate on the problem you've faced

Also, the code was updated recently, so consider to use the new version

[wlz987]

config.txt
Traceback (most recent call last):
File "/home/work/语音相关/文字转语音/vits2/train_ms.py", line 224, in
main()
File "/home/work/语音相关/文字转语音/vits2/train_ms.py", line 39, in main
mp.spawn(
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/multiprocessing/spawn.py", line 239, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/multiprocessing/spawn.py", line 197, in start_processes
while not context.join():
^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/multiprocessing/spawn.py", line 160, in join
raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 0 terminated with the following error:
Traceback (most recent call last):
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/multiprocessing/spawn.py", line 69, in _wrap
fn(i, *args)
File "/home/work/语音相关/文字转语音/vits2/train_ms.py", line 92, in run
train_and_evaluate(rank, epoch, hps, [net_g, net_d], [optim_g, optim_d], [scheduler_g, scheduler_d], scaler, [train_loader, eval_loader], logger, [writer, writer_eval])
File "/home/work/语音相关/文字转语音/vits2/train_ms.py", line 124, in train_and_evaluate
y_hat, l_length, attn, ids_slice, x_mask, z_mask, (z, z_p, m_p, logs_p, m_q, logs_q) = net_g(x, x_lengths, spec, spec_lengths, speakers)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/parallel/distributed.py", line 1156, in forward
output = self._run_ddp_forward(*inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/parallel/distributed.py", line 1110, in _run_ddp_forward
return module_to_run(*inputs[0], **kwargs[0]) # type: ignore[index]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/语音相关/文字转语音/vits2/model/models.py", line 72, in forward
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/语音相关/文字转语音/vits2/model/encoders.py", line 121, in forward
x = self.enc(x, x_mask, g=g)
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/work/语音相关/文字转语音/vits2/model/modules.py", line 47, in forward
g = self.cond_layer(g.mT).mT
^^^^^^^^^^^^^^^
File "/home/work/miniconda3/envs/vits2/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'WN' object has no attribute 'cond_layer'

[daniilrobnikov]

Hi, @wlz987 ! I checked multi-speaker training and it works fine.

I updated the code recently, so try to run the newer version.

If there any further problems, feel free to open an issue