mirror of
https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git
synced 2026-11-05 00:27:30 +00:00
[GH-ISSUE #2069] In model inference, there is no sound after the conversion【模型推理转换后播放没有声音】 #1403
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#1403
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 @uid11790 on GitHub (May 21, 2024).
Original GitHub issue: https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/2069
When using my own trained model, there is no sound during playback after conversion in model inference. However, attempting conversion with a preset model works fine.
【用自己已经训练好的模型，模型推理时，转换后播放没有声音，但是尝试用预设的模型转换却是正常的】
C:\Application\RVC1006Nvidia>runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897
2024-05-21 21:35:59 | INFO | configs.config | Found GPU NVIDIA GeForce GTX 1660 SUPER, force to fp32
2024-05-21 21:35:59 | INFO | configs.config | overwrite v1/32k.json
2024-05-21 21:35:59 | INFO | configs.config | overwrite v1/40k.json
2024-05-21 21:35:59 | INFO | configs.config | overwrite v1/48k.json
2024-05-21 21:35:59 | INFO | configs.config | overwrite v2/48k.json
2024-05-21 21:35:59 | INFO | configs.config | overwrite v2/32k.json
2024-05-21 21:35:59 | INFO | configs.config | overwrite preprocess_per to 3
2024-05-21 21:35:59 | INFO | configs.config | Half-precision floating-point: False, device: cuda:0
2024-05-21 21:36:02 | INFO | main | Use Language: zh_CN
Running on local URL: http://0.0.0.0:7897
2024-05-21 21:42:20 | INFO | main | Use gpus: 0
2024-05-21 21:42:20 | INFO | main | Execute: "runtime\python.exe" infer/modules/train/train.py -e "noboro1" -sr 40k -f0 1 -bs 3 -g 0 -te 20 -se 5 -pg assets/pretrained_v2/f0G40k.pth -pd assets/pretrained_v2/f0D40k.pth -l 1 -c 0 -sw 0 -v v2
INFO:noboro1:{'data': {'filter_length': 2048, 'hop_length': 400, 'max_wav_value': 32768.0, 'mel_fmax': None, 'mel_fmin': 0.0, 'n_mel_channels': 125, 'sampling_rate': 40000, 'win_length': 2048, 'training_files': './logs\noboro1/filelist.txt'}, 'model': {'filter_channels': 768, 'gin_channels': 256, 'hidden_channels': 192, 'inter_channels': 192, 'kernel_size': 3, 'n_heads': 2, 'n_layers': 6, 'p_dropout': 0, 'resblock': '1', 'resblock_dilation_sizes': 1, 3, 5], [1, 3, 5], [1, 3, 5, 'resblock_kernel_sizes': [3, 7, 11], 'spk_embed_dim': 109, 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'upsample_rates': [10, 10, 2, 2], 'use_spectral_norm': False}, 'train': {'batch_size': 3, 'betas': [0.8, 0.99], 'c_kl': 1.0, 'c_mel': 45, 'epochs': 20000, 'eps': 1e-09, 'fp16_run': False, 'init_lr_ratio': 1, 'learning_rate': 0.0001, 'log_interval': 200, 'lr_decay': 0.999875, 'seed': 1234, 'segment_size': 12800, 'warmup_epochs': 0}, 'model_dir': './logs\noboro1', 'experiment_dir': './logs\noboro1', 'save_every_epoch': 5, 'name': 'noboro1', 'total_epoch': 20, 'pretrainG': 'assets/pretrained_v2/f0G40k.pth', 'pretrainD': 'assets/pretrained_v2/f0D40k.pth', 'version': 'v2', 'gpus': '0', 'sample_rate': '40k', 'if_f0': 1, 'if_latest': 1, 'save_every_weights': '0', 'if_cache_data_in_gpu': 0}
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.
DEBUG:infer.lib.infer_pack.models:gin_channels: 256, self.spk_embed_dim: 109
INFO:noboro1:loaded pretrained assets/pretrained_v2/f0G40k.pth
INFO:noboro1:
INFO:noboro1:loaded pretrained assets/pretrained_v2/f0D40k.pth
INFO:noboro1:
INFO:torch.nn.parallel.distributed:Reducer buckets have been rebuilt in this iteration.
C:\Application\RVC1006Nvidia\runtime\lib\site-packages\torch\autograd_init_.py:200: UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed. This is not an error, but may impair performance.
grad.sizes() = [64, 1, 4], strides() = [4, 1, 1]
bucket_view.sizes() = [64, 1, 4], strides() = [4, 4, 1] (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\distributed\c10d\reducer.cpp:337.)
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
INFO:noboro1:Train Epoch: 1 [0%]
INFO:noboro1:[0, 0.0001]
INFO:noboro1:loss_disc=4.054, loss_gen=4.768, loss_fm=14.125,loss_mel=26.307, loss_kl=6.248
DEBUG:matplotlib:matplotlib data path: C:\Application\RVC1006Nvidia\runtime\lib\site-packages\matplotlib\mpl-data
DEBUG:matplotlib:CONFIGDIR=C:\Users\12400F.matplotlib
DEBUG:matplotlib:interactive is False
DEBUG:matplotlib:platform is win32
INFO:torch.nn.parallel.distributed:Reducer buckets have been rebuilt in this iteration.
INFO:noboro1:====> Epoch: 1 [2024-05-21 21:42:57] | (0:00:23.218699)
INFO:noboro1:====> Epoch: 2 [2024-05-21 21:43:19] | (0:00:22.203234)
INFO:noboro1:====> Epoch: 3 [2024-05-21 21:43:41] | (0:00:21.340653)
INFO:noboro1:====> Epoch: 4 [2024-05-21 21:44:03] | (0:00:22.553188)
INFO:root:Saving model and optimizer state at epoch 5 to ./logs\noboro1\G_2333333.pth
INFO:root:Saving model and optimizer state at epoch 5 to ./logs\noboro1\D_2333333.pth
INFO:noboro1:====> Epoch: 5 [2024-05-21 21:44:26] | (0:00:22.521683)
INFO:noboro1:====> Epoch: 6 [2024-05-21 21:44:48] | (0:00:21.820073)
INFO:noboro1:Train Epoch: 7 [45%]
INFO:noboro1:[200, 9.99250234335941e-05]
INFO:noboro1:loss_disc=nan, loss_gen=nan, loss_fm=nan,loss_mel=nan, loss_kl=nan
INFO:noboro1:====> Epoch: 7 [2024-05-21 21:45:10] | (0:00:21.945320)
INFO:noboro1:====> Epoch: 8 [2024-05-21 21:45:31] | (0:00:21.243423)
INFO:noboro1:====> Epoch: 9 [2024-05-21 21:45:52] | (0:00:21.422991)
INFO:root:Saving model and optimizer state at epoch 10 to ./logs\noboro1\G_2333333.pth
INFO:root:Saving model and optimizer state at epoch 10 to ./logs\noboro1\D_2333333.pth
INFO:noboro1:====> Epoch: 10 [2024-05-21 21:46:15] | (0:00:22.676498)
INFO:noboro1:====> Epoch: 11 [2024-05-21 21:46:37] | (0:00:22.207919)
INFO:noboro1:====> Epoch: 12 [2024-05-21 21:46:59] | (0:00:21.851813)
INFO:noboro1:Train Epoch: 13 [90%]
INFO:noboro1:[400, 9.98501030820433e-05]
INFO:noboro1:loss_disc=nan, loss_gen=nan, loss_fm=nan,loss_mel=nan, loss_kl=nan
INFO:noboro1:====> Epoch: 13 [2024-05-21 21:47:21] | (0:00:22.226533)
INFO:noboro1:====> Epoch: 14 [2024-05-21 21:47:43] | (0:00:21.602905)
INFO:root:Saving model and optimizer state at epoch 15 to ./logs\noboro1\G_2333333.pth
INFO:root:Saving model and optimizer state at epoch 15 to ./logs\noboro1\D_2333333.pth
INFO:noboro1:====> Epoch: 15 [2024-05-21 21:48:06] | (0:00:22.733763)
INFO:noboro1:====> Epoch: 16 [2024-05-21 21:48:27] | (0:00:21.072409)
INFO:noboro1:====> Epoch: 17 [2024-05-21 21:48:48] | (0:00:21.461390)
INFO:noboro1:====> Epoch: 18 [2024-05-21 21:49:10] | (0:00:21.399597)
INFO:noboro1:====> Epoch: 19 [2024-05-21 21:49:31] | (0:00:21.258005)
INFO:noboro1:Train Epoch: 20 [35%]
INFO:noboro1:[600, 9.976276699833672e-05]
INFO:noboro1:loss_disc=nan, loss_gen=nan, loss_fm=nan,loss_mel=nan, loss_kl=nan
INFO:root:Saving model and optimizer state at epoch 20 to ./logs\noboro1\G_2333333.pth
INFO:root:Saving model and optimizer state at epoch 20 to ./logs\noboro1\D_2333333.pth
INFO:noboro1:====> Epoch: 20 [2024-05-21 21:49:54] | (0:00:23.317478)
INFO:noboro1:Training is done. The program is closed.
INFO:noboro1:saving final ckpt:Success.
2024-05-21 21:50:41 | INFO | infer.modules.vc.modules | Get sid: noboro1.pth
2024-05-21 21:50:41 | INFO | infer.modules.vc.modules | Loading: assets/weights/noboro1.pth
2024-05-21 21:50:41 | INFO | infer.modules.vc.modules | Select index: logs\noboro1\added_IVF326_Flat_nprobe_1_noboro1_v2.index
2024-05-21 21:51:20 | INFO | infer.modules.vc.pipeline | Loading rmvpe model,assets/rmvpe/rmvpe.pt
2024-05-21 21:51:25 | ERROR | root | Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
File "asyncio\events.py", line 80, in _run
File "asyncio\proactor_events.py", line 162, in _call_connection_lost
ConnectionResetError: [WinError 10054] 远程主机强迫关闭了一个现有的连接。
@Xmug commented on GitHub (Nov 22, 2025):
我也遇到这个问题了，想问下你解决这个问题了吗？