You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
"/usr/local/bin/python" GPT_SoVITS/s1_train.py --config_file "/content/GPT-SoVITS/TEMP/tmp_s1.yaml"
Seed set to 1234
Using 16bit Automatic Mixed Precision (AMP)
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_lightning_module.py:26: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
77.6 M Trainable params
0 Non-trainable params
77.6 M Total params
310.426 Total estimated model params size (MB)
257 Modules in train mode
0 Modules in eval mode
/usr/local/lib/python3.9/site-packages/torch/utils/data/dataloader.py:617: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
bert_feature = torch.load(path_bert, map_location="cpu")
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
bert_feature = torch.load(path_bert, map_location="cpu")
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
bert_feature = torch.load(path_bert, map_location="cpu")
/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py:310: The number of training batches (30) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch.
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
bert_feature = torch.load(path_bert, map_location="cpu")
Epoch 0: 0% 0/30 [00:00<?, ?it/s] [rank0]: Traceback (most recent call last):
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/s1_train.py", line 183, in
[rank0]: main(args)
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/s1_train.py", line 159, in main
[rank0]: trainer.fit(model, data_module, ckpt_path=ckpt_path)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 539, in fit
[rank0]: call._call_and_handle_interrupt(
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 46, in _call_and_handle_interrupt
[rank0]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 105, in launch
[rank0]: return function(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 575, in _fit_impl
[rank0]: self._run(model, ckpt_path=ckpt_path)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 982, in _run
[rank0]: results = self._run_stage()
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1026, in _run_stage
[rank0]: self.fit_loop.run()
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 216, in run
[rank0]: self.advance()
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 455, in advance
[rank0]: self.epoch_loop.run(self._data_fetcher)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 150, in run
[rank0]: self.advance(data_fetcher)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 322, in advance
[rank0]: batch_output = self.manual_optimization.run(kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/manual.py", line 94, in run
[rank0]: self.advance(kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/manual.py", line 114, in advance
[rank0]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values())
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 323, in _call_strategy_hook
[rank0]: output = fn(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 390, in training_step
[rank0]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 641, in call
[rank0]: wrapper_output = wrapper_module(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1643, in forward
[rank0]: else self._run_ddp_forward(*inputs, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1459, in _run_ddp_forward
[rank0]: return self.module(*inputs, **kwargs) # type: ignore[index]
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank0]: return forward_call(args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 634, in wrapped_forward
[rank0]: out = method(_args, **_kwargs)
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_lightning_module.py", line 39, in training_step
[rank0]: loss, acc = forward(
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_model.py", line 428, in forward
[rank0]: acc = self.ar_accuracy_metric(logits.permute(0, 2, 1).detach(), targets).item()
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 316, in forward
[rank0]: self._forward_cache = self._forward_reduce_state_update(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 385, in _forward_reduce_state_update
[rank0]: self.update(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 560, in wrapped_func
[rank0]: raise err
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 550, in wrapped_func
[rank0]: update(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/classification/stat_scores.py", line 343, in update
[rank0]: tp, fp, tn, fn = _multiclass_stat_scores_update(
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/functional/classification/stat_scores.py", line 398, in _multiclass_stat_scores_update
[rank0]: preds_oh = _refine_preds_oh(preds, preds_oh, target, top_k)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/functional/classification/stat_scores.py", line 364, in refine_preds_oh
[rank0]: return torch.zeros_like(preds_oh, dtype=torch.int32).scatter(-1, result.unsqueeze(1).unsqueeze(1), 1)
[rank0]: RuntimeError: Index tensor must have the same number of dimensions as self tensor
Epoch 0: 0%| | 0/30 [00:02<?, ?it/s]
The text was updated successfully, but these errors were encountered:
"/usr/local/bin/python" GPT_SoVITS/s1_train.py --config_file "/content/GPT-SoVITS/TEMP/tmp_s1.yaml"
Seed set to 1234
Using 16bit Automatic Mixed Precision (AMP)
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_lightning_module.py:26: You are using
torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.ckpt_path: None
Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/1
distributed_backend=nccl
All distributed processes registered. Starting with 1 processes
semantic_data_len: 24
phoneme_data_len: 24
item_name semantic_audio
0 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 271 360 496 421 233 43 573...
1 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 72 140 884 339 437 510 759 847...
2 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 234 234 72 214 514 102 275 955 169...
3 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 54 271 271 271 72 505 804 543 462 958 169 169 ...
4 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 53 271 271 41 496 187 448 603 801 ...
5 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 29 272 666 406 180 230 705...
6 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 360 644 850 484 1013 592 915 2...
7 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 242 350 339 1018 610 16...
8 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 540 272 850 117 635 126...
9 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 41 271 72 540 114 163 480 665 134 ...
10 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 570 341 108 380 978 518...
11 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 72 72 242 243 147 791 322 201 541 117 1022...
12 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 609 2 376 653 928 403 7...
13 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 72 271 72 540 177 1023 934 396 312 926 164...
14 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 105 105 271 72 242 1015 204 822 884 37...
15 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 162 311 575 995 126 434...
16 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 72 875 72 17 227 641 627 768 422 632 422 6...
17 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 54 271 271 271 234 72 721 339 394 788 612 170 ...
18 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 105 105 271 570 579 621 330 723 277 23...
19 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 505 75 391 157 20 552 192 ...
20 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 492 578 497 944 359 829 91...
21 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 17 748 187 93 119 415 7...
22 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 271 271 271 271 72 13 196 478 373 306 939 ...
23 1_1_1_original_(Vocals)(No Echo)(No Noise).w... 520 72 72 540 520 72 913 535 47 160 592 715 62...
deleted 2 audios who's phoneme/sec are bigger than 25 or smaller than 3
dataset.len(): 88
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
| Name | Type | Params | Mode
0 | model | Text2SemanticDecoder | 77.6 M | train
77.6 M Trainable params
0 Non-trainable params
77.6 M Total params
310.426 Total estimated model params size (MB)
257 Modules in train mode
0 Modules in eval mode
/usr/local/lib/python3.9/site-packages/torch/utils/data/dataloader.py:617: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using
torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.bert_feature = torch.load(path_bert, map_location="cpu")
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using
torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.bert_feature = torch.load(path_bert, map_location="cpu")
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using
torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.bert_feature = torch.load(path_bert, map_location="cpu")
/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py:310: The number of training batches (30) is smaller than the logging interval Trainer(log_every_n_steps=50). Set a lower value for log_every_n_steps if you want to see logs for the training epoch.
/content/GPT-SoVITS/GPT_SoVITS/AR/data/dataset.py:230: FutureWarning: You are using
torch.loadwithweights_only=False(the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value forweights_onlywill be flipped toTrue. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user viatorch.serialization.add_safe_globals. We recommend you start settingweights_only=Truefor any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.bert_feature = torch.load(path_bert, map_location="cpu")
Epoch 0: 0% 0/30 [00:00<?, ?it/s] [rank0]: Traceback (most recent call last):
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/s1_train.py", line 183, in
[rank0]: main(args)
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/s1_train.py", line 159, in main
[rank0]: trainer.fit(model, data_module, ckpt_path=ckpt_path)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 539, in fit
[rank0]: call._call_and_handle_interrupt(
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 46, in _call_and_handle_interrupt
[rank0]: return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 105, in launch
[rank0]: return function(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 575, in _fit_impl
[rank0]: self._run(model, ckpt_path=ckpt_path)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 982, in _run
[rank0]: results = self._run_stage()
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1026, in _run_stage
[rank0]: self.fit_loop.run()
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 216, in run
[rank0]: self.advance()
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 455, in advance
[rank0]: self.epoch_loop.run(self._data_fetcher)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 150, in run
[rank0]: self.advance(data_fetcher)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/training_epoch_loop.py", line 322, in advance
[rank0]: batch_output = self.manual_optimization.run(kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/manual.py", line 94, in run
[rank0]: self.advance(kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/loops/optimization/manual.py", line 114, in advance
[rank0]: training_step_output = call._call_strategy_hook(trainer, "training_step", *kwargs.values())
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/trainer/call.py", line 323, in _call_strategy_hook
[rank0]: output = fn(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 390, in training_step
[rank0]: return self._forward_redirection(self.model, self.lightning_module, "training_step", *args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 641, in call
[rank0]: wrapper_output = wrapper_module(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1643, in forward
[rank0]: else self._run_ddp_forward(*inputs, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1459, in _run_ddp_forward
[rank0]: return self.module(*inputs, **kwargs) # type: ignore[index]
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank0]: return forward_call(args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/pytorch_lightning/strategies/strategy.py", line 634, in wrapped_forward
[rank0]: out = method(_args, **_kwargs)
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_lightning_module.py", line 39, in training_step
[rank0]: loss, acc = forward(
[rank0]: File "/content/GPT-SoVITS/GPT_SoVITS/AR/models/t2s_model.py", line 428, in forward
[rank0]: acc = self.ar_accuracy_metric(logits.permute(0, 2, 1).detach(), targets).item()
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank0]: return self._call_impl(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
[rank0]: return forward_call(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 316, in forward
[rank0]: self._forward_cache = self._forward_reduce_state_update(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 385, in _forward_reduce_state_update
[rank0]: self.update(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 560, in wrapped_func
[rank0]: raise err
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/metric.py", line 550, in wrapped_func
[rank0]: update(*args, **kwargs)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/classification/stat_scores.py", line 343, in update
[rank0]: tp, fp, tn, fn = _multiclass_stat_scores_update(
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/functional/classification/stat_scores.py", line 398, in _multiclass_stat_scores_update
[rank0]: preds_oh = _refine_preds_oh(preds, preds_oh, target, top_k)
[rank0]: File "/usr/local/lib/python3.9/site-packages/torchmetrics/functional/classification/stat_scores.py", line 364, in refine_preds_oh
[rank0]: return torch.zeros_like(preds_oh, dtype=torch.int32).scatter(-1, result.unsqueeze(1).unsqueeze(1), 1)
[rank0]: RuntimeError: Index tensor must have the same number of dimensions as self tensor
Epoch 0: 0%| | 0/30 [00:02<?, ?it/s]
The text was updated successfully, but these errors were encountered: