search

RVC-Project / Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!
MIT License
23.11k stars 3.46k forks source link

No index/ .index file creation? #2067

Closed zaneburko closed 4 months ago

zaneburko commented 4 months ago

I did everything properly. Let my model train, but I can't find the .index file. Anyone know a fix?

2024-05-19 14:12:25 | INFO | main | Use Language: en_US Running on local URL: http://0.0.0.0:7865 IMPORTANT: You are using gradio version 4.23.0, however version 4.29.0 is available, please upgrade.

2024-05-19 14:12:44 | WARNING | main | assets/pretrained_v2/f0G48k.pth not exist, will not use pretrained model 2024-05-19 14:12:44 | WARNING | main | assets/pretrained_v2/f0D48k.pth not exist, will not use pretrained model 2024-05-19 14:12:45 | WARNING | main | assets/pretrained_v2/G48k.pth not exist, will not use pretrained model 2024-05-19 14:12:45 | WARNING | main | assets/pretrained_v2/D48k.pth not exist, will not use pretrained model 2024-05-19 14:14:33 | INFO | main | Execute: "D:\Users\zaneb\miniconda3\envs\rvc-env\python.exe" infer/modules/train/preprocess.py "C:\Users\zaneb\Downloads\Archive" 48000 3 "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane" False 3.0 C:\Users\zaneb\Downloads\Archive 48000 3 C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane False 3.0 start preprocess C:\Users\zaneb\Downloads\Archive 48000 3 C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane False 3.0 C:\Users\zaneb\Downloads\Archive 48000 3 C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane False 3.0 C:\Users\zaneb\Downloads\Archive 48000 3 C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane False 3.0 C:\Users\zaneb\Downloads\Archive/1UNBOXING NIKE LOWCOAST DUNKS! Akashoe Unboxing Zane Burko(Vocals).mp3 -> Traceback (most recent call last): File "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI\infer\lib\audio.py", line 37, in load_audio ffmpeg.input(file, threads=0) File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\ffmpeg_run.py", line 313, in run process = run_async( File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\ffmpeg_run.py", line 284, in run_async return subprocess.Popen( File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\subprocess.py", line 971, in init self._execute_child(args, executable, preexec_fn, close_fds, File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\subprocess.py", line 1456, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] The system cannot find the file specified

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI\infer\modules\train\preprocess.py", line 83, in pipeline audio = load_audio(path, self.sr) File "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI\infer\lib\audio.py", line 42, in load_audio raise RuntimeError(f"Failed to load audio: {e}") RuntimeError: Failed to load audio: [WinError 2] The system cannot find the file specified C:\Users\zaneb\Downloads\Archive/3_UNBOXING BAPESTA MIST GREYROYAL PURPLE COURTSTAS! Fashoes Unboxing Zane Burko(Vocals).mp3 -> Traceback (most recent call last): File "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI\infer\lib\audio.py", line 37, in load_audio ffmpeg.input(file, threads=0) File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\ffmpeg_run.py", line 313, in run process = run_async( File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\ffmpeg_run.py", line 284, in run_async return subprocess.Popen( File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\subprocess.py", line 971, in init self._execute_child(args, executable, preexec_fn, close_fds, File "D:\Users\zaneb\miniconda3\envs\rvc-env\lib\subprocess.py", line 1456, in _execute_child hp, ht, pid, tid = _winapi.CreateProcess(executable, args, FileNotFoundError: [WinError 2] The system cannot find the file specified

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI\infer\modules\train\preprocess.py", line 83, in pipeline audio = load_audio(path, self.sr) File "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI\infer\lib\audio.py", line 42, in load_audio raise RuntimeError(f"Failed to load audio: {e}") RuntimeError: Failed to load audio: [WinError 2] The system cannot find the file specified

2024-05-19 14:19:22 | INFO | main | Execute: "D:\Users\zaneb\miniconda3\envs\rvc-env\python.exe" infer/modules/train/extract_feature_print.py cpu 1 0 0 "C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane" v2 False infer/modules/train/extract_feature_print.py cpu 1 0 0 C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane v2 False exp_dir: C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane load model(s) from assets/hubert/hubert_base.pt 2024-05-19 14:19:25 | INFO | fairseq.tasks.hubert_pretraining | current directory is C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI 2024-05-19 14:19:25 | INFO | fairseq.tasks.hubert_pretraining | HubertPretrainingTask Config {'_name': 'hubert_pretraining', 'data': 'metadata', 'fine_tuning': False, 'labels': ['km'], 'label_dir': 'label', 'label_rate': 50.0, 'sample_rate': 16000, 'normalize': False, 'enable_padding': False, 'max_keep_size': None, 'max_sample_size': 250000, 'min_sample_size': 32000, 'single_target': False, 'random_crop': True, 'pad_audio': False} 2024-05-19 14:19:25 | INFO | fairseq.models.hubert.hubert | HubertModel Config: {'_name': 'hubert', 'label_rate': 50.0, 'extractor_mode': default, 'encoder_layers': 12, 'encoder_embed_dim': 768, 'encoder_ffn_embed_dim': 3072, 'encoder_attention_heads': 12, 'activation_fn': gelu, 'layer_type': transformer, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'encoder_layerdrop': 0.05, 'dropout_input': 0.1, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': False, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] 4 + [(512,2,2)] 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 0.1, 'mask_length': 10, 'mask_prob': 0.8, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'checkpoint_activations': False, 'required_seq_len_multiple': 2, 'depthwise_conv_kernel_size': 31, 'attn_type': '', 'pos_enc_type': 'abs', 'fp16': False} D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\torch\nn\utils\weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") move model to cpu no-feature-todo 2024-05-19 14:19:27 | INFO | main | infer/modules/train/extract/extract_f0_print.py C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane 3 dio no-f0-todo no-f0-todo no-f0-todo infer/modules/train/extract_feature_print.py cpu 1 0 0 C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane v2 False exp_dir: C:\Users\zaneb\Retrieval-based-Voice-Conversion-WebUI/logs/zane load model(s) from assets/hubert/hubert_base.pt move model to cpu no-feature-todo

2024-05-19 14:19:56 | INFO | main | Use gpus: 2024-05-19 14:19:56 | INFO | main | No pretrained Generator 2024-05-19 14:19:56 | INFO | main | No pretrained Discriminator 2024-05-19 14:19:56 | INFO | main | Execute: "D:\Users\zaneb\miniconda3\envs\rvc-env\python.exe" infer/modules/train/train.py -e "zane" -sr 48k -f0 1 -bs 4 -te 350 -se 25 -l 1 -c 0 -sw 0 -v v2 NO GPU DETECTED: falling back to CPU - this may take a while INFO:zane:{'data': {'filter_length': 2048, 'hop_length': 480, 'max_wav_value': 32768.0, 'mel_fmax': None, 'mel_fmin': 0.0, 'n_mel_channels': 128, 'sampling_rate': 48000, 'win_length': 2048, 'training_files': './logs\zane/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': [24, 20, 4, 4], 'upsample_rates': [12, 10, 2, 2], 'use_spectral_norm': False}, 'train': {'batch_size': 4, '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': 17280, 'warmup_epochs': 0}, 'model_dir': './logs\zane', 'experiment_dir': './logs\zane', 'save_every_epoch': 25, 'name': 'zane', 'total_epoch': 350, 'pretrainG': '', 'pretrainD': '', 'version': 'v2', 'gpus': '0', 'sample_rate': '48k', 'if_f0': 1, 'if_latest': 1, 'save_every_weights': '0', 'if_cache_data_in_gpu': 0} D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\torch\nn\utils\weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") DEBUG:infer.lib.infer_pack.models:gin_channels: 256, self.spk_embed_dim: 109 D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\torch\autograd\graph.py:744: 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 ..\torch\csrc\distributed\c10d\reducer.cpp:339.) return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass INFO:zane:Train Epoch: 1 [0%] INFO:zane:[0, 0.0001] INFO:zane:loss_disc=8.836, loss_gen=7.659, loss_fm=0.130,loss_mel=75.000, loss_kl=9.000 DEBUG:matplotlib:matplotlib data path: D:\Users\zaneb\miniconda3\envs\rvc-env\lib\site-packages\matplotlib\mpl-data DEBUG:matplotlib:CONFIGDIR=C:\Users\zaneb.matplotlib DEBUG:matplotlib:interactive is False DEBUG:matplotlib:platform is win32 INFO:root:Saving model and optimizer state at epoch 350 to ./logs\zane\G_2333333.pth INFO:root:Saving model and optimizer state at epoch 350 to ./logs\zane\D_2333333.pth INFO:zane:====> Epoch: 350 [2024-05-19 15:04:02] | (0:00:08.492908) INFO:zane:Training is done. The program is closed. INFO:zane:saving final ckpt:Success.

fumiama commented 4 months ago

... assets/pretrained_v2/f0G48k.pth not exist ... FileNotFoundError: [WinError 2] The system cannot find the file specified

Please read the README carefully. You said that you did everything properly, but it's clear that you missed to download the pre-models, which is mentioned in README.