mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-11-05 00:27:30 +00:00
[GH-ISSUE #234] 开始转换声音会闪退 #113
Labels
No labels
AMD/Intel
bug
bug
bug
colab
dependencies
documentation
duplicate
enhancement
following up
good first issue
help wanted
invalid
question
stale
stale
stale
todo list
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
RVC-Project/Retrieval-based-Voice-Conversion-WebUI#113
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @kirari3 on GitHub (May 5, 2023).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/234
使用群内提供的模型后出现这个错误 请问这要如何解决 谢谢作者大大们
@kirari3 commented on GitHub (May 5, 2023):
本人使用的是16系显卡（1660ti）不知道是否和这个有关 我训练的时候也没有index和pth这两个文件 但0428版本不是已经解锁了16系显卡嘛
@RVC-Boss commented on GitHub (May 6, 2023):
选错模型了，要选weights文件夹下60MB的那个
@kirari3 commented on GitHub (May 6, 2023):
你好 我选择是群内提供的模型 依旧会有这种情况 我也询问过其他使用相同模型的群友 他们并没有任何闪退的情况
@kirari3 commented on GitHub (May 6, 2023):
此外 我刚刚自己训练了一个模型 这次weight里面有pth文件了 但是选择了之后依然有闪退的情况
以下是我的训练日志
2023-05-06 12:42:45,951 haha2 INFO {'train': {'log_interval': 200, 'seed': 1234, 'epochs': 20000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 3, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 12800, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0}, 'data': {'max_wav_value': 32768.0, 'sampling_rate': 40000, 'filter_length': 2048, 'hop_length': 400, 'win_length': 2048, 'n_mel_channels': 125, 'mel_fmin': 0.0, 'mel_fmax': None, 'training_files': './logs\haha2/filelist.txt'}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': 1, 3, 5], [1, 3, 5], [1, 3, 5, 'upsample_rates': [10, 10, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'use_spectral_norm': False, 'gin_channels': 256, 'spk_embed_dim': 109}, 'model_dir': './logs\haha2', 'experiment_dir': './logs\haha2', 'save_every_epoch': 5, 'name': 'haha2', 'total_epoch': 20, 'pretrainG': 'pretrained/f0G40k.pth', 'pretrainD': 'pretrained/f0D40k.pth', 'gpus': '0', 'sample_rate': '40k', 'if_f0': 1, 'if_latest': 0, 'if_cache_data_in_gpu': 0}
2023-05-06 12:42:45,952 haha2 WARNING D:\aivc\RVC-beta\train is not a git repository, therefore hash value comparison will be ignored.
2023-05-06 12:42:47,591 haha2 INFO loaded pretrained pretrained/f0G40k.pth pretrained/f0D40k.pth
2023-05-06 12:43:02,871 haha2 INFO Train Epoch: 1 [0%]
2023-05-06 12:43:02,876 haha2 INFO [0, 0.0001]
2023-05-06 12:43:02,876 haha2 INFO loss_disc=3.229, loss_gen=3.412, loss_fm=10.321,loss_mel=24.430, loss_kl=5.000
2023-05-06 12:43:13,212 haha2 INFO ====> Epoch: 1
2023-05-06 12:43:23,259 haha2 INFO ====> Epoch: 2
2023-05-06 12:43:33,780 haha2 INFO ====> Epoch: 3
2023-05-06 12:43:43,871 haha2 INFO ====> Epoch: 4
2023-05-06 12:43:53,971 haha2 INFO Saving model and optimizer state at epoch 5 to ./logs\haha2\G_65.pth
2023-05-06 12:43:54,901 haha2 INFO Saving model and optimizer state at epoch 5 to ./logs\haha2\D_65.pth
2023-05-06 12:44:01,797 haha2 INFO ====> Epoch: 5
2023-05-06 12:44:12,043 haha2 INFO ====> Epoch: 6
2023-05-06 12:44:22,153 haha2 INFO ====> Epoch: 7
2023-05-06 12:44:32,698 haha2 INFO ====> Epoch: 8
2023-05-06 12:44:43,245 haha2 INFO ====> Epoch: 9
2023-05-06 12:44:53,941 haha2 INFO Saving model and optimizer state at epoch 10 to ./logs\haha2\G_130.pth
2023-05-06 12:44:54,779 haha2 INFO Saving model and optimizer state at epoch 10 to ./logs\haha2\D_130.pth
2023-05-06 12:45:01,168 haha2 INFO ====> Epoch: 10
2023-05-06 12:45:11,798 haha2 INFO ====> Epoch: 11
2023-05-06 12:45:22,368 haha2 INFO ====> Epoch: 12
2023-05-06 12:45:31,596 haha2 INFO ====> Epoch: 13
2023-05-06 12:45:40,232 haha2 INFO ====> Epoch: 14
2023-05-06 12:45:48,978 haha2 INFO Saving model and optimizer state at epoch 15 to ./logs\haha2\G_195.pth
2023-05-06 12:45:49,594 haha2 INFO Saving model and optimizer state at epoch 15 to ./logs\haha2\D_195.pth
2023-05-06 12:45:53,089 haha2 INFO ====> Epoch: 15
2023-05-06 12:45:57,270 haha2 INFO Train Epoch: 16 [38%]
2023-05-06 12:45:57,274 haha2 INFO [200, 9.981266397366609e-05]
2023-05-06 12:45:57,275 haha2 INFO loss_disc=3.388, loss_gen=2.938, loss_fm=7.138,loss_mel=20.546, loss_kl=1.940
2023-05-06 12:46:02,404 haha2 INFO ====> Epoch: 16
2023-05-06 12:46:11,007 haha2 INFO ====> Epoch: 17
2023-05-06 12:46:19,546 haha2 INFO ====> Epoch: 18
2023-05-06 12:46:28,042 haha2 INFO ====> Epoch: 19
2023-05-06 12:46:36,525 haha2 INFO Saving model and optimizer state at epoch 20 to ./logs\haha2\G_260.pth
2023-05-06 12:46:37,273 haha2 INFO Saving model and optimizer state at epoch 20 to ./logs\haha2\D_260.pth
2023-05-06 12:46:39,799 haha2 INFO ====> Epoch: 20
2023-05-06 12:46:39,799 haha2 INFO Training is done. The program is closed.
2023-05-06 12:46:40,054 haha2 INFO saving final ckpt:Success.
请过目一下 谢谢
@kirari3 commented on GitHub (May 6, 2023):
软件设置情况
@Duo1a commented on GitHub (Jan 8, 2026):
我也是，一打开“开始音频转换”就卡住了，cmd没有一点变化