AttributeError: 'HParams' object has no attribute 'dataset_type'

[EstelleSchwarzer]

系统平台: windows

出现问题的环节: 推理

Python版本: 3.8

PyTorch版本: 1.13.1+cu116

所用分支: 4.0-v2

所用数据集:

授权证明截图:

问题描述: 推理报错，AttributeError: 'HParams' object has no attribute 'dataset_type'，4.0分支可以正常推

日志截图:

use_cuda, True
INFO:44k:{'log_interval': 200, 'eval_interval': 800, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 6, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 10240, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0, 'use_sr': True, 'max_speclen': 512, 'port': '8001', 'keep_ckpts': 10}
INFO:44k:{'training_files': 'filelists/train.txt', 'validation_files': 'filelists/val.txt', 'max_wav_value': 32768.0, 'sampling_rate': 44100, 'filter_length': 2048, 'hop_length': 512, 'win_length': 2048, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': 22050}
INFO:44k:{'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [8, 8, 2, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256, 'ssl_dim': 256, 'n_speakers': 200}
INFO:torch.distributed.distributed_c10d:Added key: store_based_barrier_key:1 to store for rank: 0
INFO:torch.distributed.distributed_c10d:Rank 0: Completed store-based barrier for key:store_based_barrier_key:1 with 1 nodes.
Traceback (most recent call last):
File "train.py", line 435, in
main()
File "train.py", line 57, in main
mp.spawn(run, nprocs=n_gpus, args=(n_gpus, hps,))
File "D:\so-vits\so-vits-svc1\python38\lib\site-packages\torch\multiprocessing\spawn.py", line 240, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "D:\so-vits\so-vits-svc1\python38\lib\site-packages\torch\multiprocessing\spawn.py", line 198, in start_processes while not context.join():
File "D:\so-vits\so-vits-svc1\python38\lib\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 "D:\so-vits\so-vits-svc1\python38\lib\site-packages\torch\multiprocessing\spawn.py", line 69, in _wrap
fn(i, *args)
File "D:\so-vits\so-vits-svc1\train.py", line 76, in run
dataset_constructor = DatasetConstructor(hps, num_replicas=n_gpus, rank=rank)
File "D:\so-vits\so-vits-svc1\data_utils.py", line 293, in init
self._get_components()
File "D:\so-vits\so-vits-svc1\data_utils.py", line 296, in _get_components
self._init_datasets()
File "D:\so-vits\so-vits-svc1\data_utils.py", line 301, in _init_datasets
self._train_dataset = self.dataset_function[self.hparams.data.dataset_type](self.hparams,
AttributeError: 'HParams' object has no attribute 'dataset_type'

[NaruseMioShirakana]

配置文件错了，请检查你的配置文件

[EstelleSchwarzer]

配置文件错了，请检查你的配置文件

好的，谢谢回复，我用模板重新配置一下

[Miuzarte]

配置文件错了，请检查你的配置文件

好的，谢谢回复，我用模板重新配置一下

重新执行一遍划分数据集和生成配置文件的那条命令就好了