Copied file to input/351b84a7-8622-4c51-a803-ae848d62d158/origin.mp3 执行完毕，请检查输出文件 2024-06-19 22:59:23,923 - modelscope - INFO - PyTorch version 2.0.1+cu118 Found. 2024-06-19 22:59:23,924 - modelscope - INFO - Loading ast index from /root/.cache/modelscope/ast_indexer 2024-06-19 22:59:23,924 - modelscope - INFO - No valid ast index found from /root/.cache/modelscope/ast_indexer, generating ast index from prebuilt! 2024-06-19 22:59:23,996 - modelscope - INFO - Loading done! Current index file version is 1.10.0, with md5 b51edac0938f2bdbb763b5eb2eac94ee and a total number of 946 components indexed 2024-06-19 22:59:29,620 - modelscope - WARNING - Model revision not specified, use revision: v1.0.2 Downloading: 0%| | 0.00/1.45k [00:00标注文件路径: /src/output/351b84a7-8622-4c51-a803-ae848d62d158/asr_opt/denoise_opt.list "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/prepare_datasets/1-get-text.py "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/prepare_datasets/1-get-text.py ('进度：1a-ing', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) IMPORTANT: You are using gradio version 3.38.0, however version 4.29.0 is available, please upgrade. -------- Building prefix dict from the default dictionary ... Dumping model to file cache /src/TEMP/jieba.cache Loading model cost 1.245 seconds. Prefix dict has been built succesfully. ('进度：1a-done', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py ('进度：1a-done, 1b-ing', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) ('进度：1a1b-done', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/prepare_datasets/3-get-semantic.py "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/prepare_datasets/3-get-semantic.py ('进度：1a1b-done, 1cing', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) ('进度：all-done', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) ('一键三连进程结束', {'__type__': 'update', 'visible': True}, {'__type__': 'update', 'visible': False}) ('SoVITS训练开始："/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/s2_train.py --config "/src/TEMP/tmp_s2.json"', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/s2_train.py --config "/src/TEMP/tmp_s2.json" IMPORTANT: You are using gradio version 3.38.0, however version 4.29.0 is available, please upgrade. -------- INFO:351b84a7-8622-4c51-a803-ae848d62d158:{'train': {'log_interval': 100, 'eval_interval': 500, 'seed': 1234, 'epochs': 8, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 11, 'fp16_run': True, 'lr_decay': 0.999875, 'segment_size': 20480, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0, 'text_low_lr_rate': 0.4, 'pretrained_s2G': 'GPT_SoVITS/pretrained_models/s2G488k.pth', 'pretrained_s2D': 'GPT_SoVITS/pretrained_models/s2D488k.pth', 'if_save_latest': True, 'if_save_every_weights': True, 'save_every_epoch': 4, 'gpu_numbers': '0-1'}, 'data': {'max_wav_value': 32768.0, 'sampling_rate': 32000, 'filter_length': 2048, 'hop_length': 640, 'win_length': 2048, 'n_mel_channels': 128, 'mel_fmin': 0.0, 'mel_fmax': None, 'add_blank': True, 'n_speakers': 300, 'cleaned_text': True, 'exp_dir': 'logs/351b84a7-8622-4c51-a803-ae848d62d158'}, 'model': {'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': [10, 8, 2, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 8, 2, 2], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 512, 'semantic_frame_rate': '25hz', 'freeze_quantizer': True}, 's2_ckpt_dir': 'logs/351b84a7-8622-4c51-a803-ae848d62d158', 'content_module': 'cnhubert', 'save_weight_dir': 'SoVITS_weights', 'name': '351b84a7-8622-4c51-a803-ae848d62d158', 'pretrain': None, 'resume_step': None} 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. phoneme_data_len: 1 wav_data_len: 100 0%| | 0/100 [00:00 INFO:351b84a7-8622-4c51-a803-ae848d62d158:loaded pretrained GPT_SoVITS/pretrained_models/s2D488k.pth /root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/torch/optim/lr_scheduler.py:139: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`. Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate warnings.warn("Detected call of `lr_scheduler.step()` before `optimizer.step()`. " 0%| | 0/10 [00:00 Epoch: 1 0%| | 0/10 [00:00 Epoch: 2 0%| | 0/10 [00:00 Epoch: 3 0%| | 0/10 [00:00 Epoch: 4 0%| | 0/10 [00:00 Epoch: 5 0%| | 0/10 [00:00 Epoch: 6 0%| | 0/10 [00:00 Epoch: 7 0%| | 0/10 [00:00 Epoch: 8 ('SoVITS训练完成', {'__type__': 'update', 'visible': True}, {'__type__': 'update', 'visible': False}) ('GPT训练开始："/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/s1_train.py --config_file "/src/TEMP/tmp_s1.yaml" ', {'__type__': 'update', 'visible': False}, {'__type__': 'update', 'visible': True}) "/root/.pyenv/versions/3.9.19/bin/python" GPT_SoVITS/s1_train.py --config_file "/src/TEMP/tmp_s1.yaml" IMPORTANT: You are using gradio version 3.38.0, however version 4.29.0 is available, please upgrade. -------- 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 ckpt_path: None [rank: 0] Seed set to 1234 Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/1 ---------------------------------------------------------------------------------------------------- distributed_backend=nccl All distributed processes registered. Starting with 1 processes ---------------------------------------------------------------------------------------------------- Missing logger folder: logs/351b84a7-8622-4c51-a803-ae848d62d158/logs_s1/logs_s1 semantic_data_len: 1 phoneme_data_len: 1 item_name semantic_audio 0 origin.mp3_0000000000_0000508480.wav 520 721 1005 578 283 919 290 96 142 545 8 17 7... dataset.__len__(): 100 LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1] | Name | Type | Params | Mode ------------------------------------------------------- 0 | model | Text2SemanticDecoder | 77.5 M | train ------------------------------------------------------- 77.5 M Trainable params 0 Non-trainable params 77.5 M Total params 309.975 Total estimated model params size (MB) /root/.pyenv/versions/3.9.19/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py:298: The number of training batches (10) 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. Training: | | 0/? [00:00