GPT-SoVITS模型|范长老配音模型范长老AI模型

适合类型：擅长领域：美食/影视/动漫/纪录片/百科/小说真实自然，朗朗动听

模型配音效果

训练日志

2025-07-30 15:22:13,598	范长老	INFO	{'train': {'log_interval': 100, 'eval_interval': 500, 'seed': 1234, 'epochs': 20, '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': 20, 'gpu_numbers': '0'}, '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/范长老'}, '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/范长老', 'content_module': 'cnhubert', 'save_weight_dir': 'SoVITS_weights', 'name': '范长老', 'pretrain': None, 'resume_step': None}
2025-07-30 15:22:14,872	范长老	INFO	loaded pretrained GPT_SoVITS/pretrained_models/s2G488k.pth
2025-07-30 15:22:15,076	范长老	INFO	loaded pretrained GPT_SoVITS/pretrained_models/s2D488k.pth
2025-07-30 15:22:45,720	范长老	INFO	Train Epoch: 1 [0%]
2025-07-30 15:22:45,720	范长老	INFO	[2.516481399536133, 2.307490825653076, 10.406949996948242, 19.013336181640625, 0.0, 2.022042989730835, 0, 9.99875e-05]
2025-07-30 15:22:58,434	范长老	INFO	====> Epoch: 1
2025-07-30 15:23:11,008	范长老	INFO	====> Epoch: 2
2025-07-30 15:23:23,800	范长老	INFO	====> Epoch: 3
2025-07-30 15:23:36,191	范长老	INFO	====> Epoch: 4
2025-07-30 15:23:48,337	范长老	INFO	====> Epoch: 5
2025-07-30 15:24:00,778	范长老	INFO	====> Epoch: 6
2025-07-30 15:24:09,886	范长老	INFO	Train Epoch: 7 [67%]
2025-07-30 15:24:09,887	范长老	INFO	[2.6658687591552734, 2.1377224922180176, 8.916056632995605, 16.089149475097656, 0.0, 1.3195579051971436, 100, 9.991253280566489e-05]
2025-07-30 15:24:13,468	范长老	INFO	====> Epoch: 7
2025-07-30 15:24:25,827	范长老	INFO	====> Epoch: 8
2025-07-30 15:24:38,372	范长老	INFO	====> Epoch: 9
2025-07-30 15:24:50,912	范长老	INFO	====> Epoch: 10
2025-07-30 15:25:02,878	范长老	INFO	====> Epoch: 11
2025-07-30 15:25:15,528	范长老	INFO	====> Epoch: 12
2025-07-30 15:25:28,952	范长老	INFO	====> Epoch: 13
2025-07-30 15:25:37,544	范长老	INFO	Train Epoch: 14 [33%]
2025-07-30 15:25:37,544	范长老	INFO	[2.6347570419311523, 2.4107916355133057, 9.478985786437988, 16.548810958862305, 0.0, 1.5678279399871826, 200, 9.982514211643064e-05]
2025-07-30 15:25:53,851	范长老	INFO	====> Epoch: 14
2025-07-30 15:26:18,855	范长老	INFO	====> Epoch: 15
2025-07-30 15:26:39,560	范长老	INFO	====> Epoch: 16
2025-07-30 15:27:04,692	范长老	INFO	====> Epoch: 17
2025-07-30 15:27:28,784	范长老	INFO	====> Epoch: 18
2025-07-30 15:27:42,210	范长老	INFO	====> Epoch: 19
2025-07-30 15:27:54,865	范长老	INFO	Saving model and optimizer state at iteration 20 to logs/范长老/logs_s2\G_233333333333.pth
2025-07-30 15:27:55,740	范长老	INFO	Saving model and optimizer state at iteration 20 to logs/范长老/logs_s2\D_233333333333.pth
2025-07-30 15:27:56,991	范长老	INFO	saving ckpt 范长老_e20:Success.
2025-07-30 15:27:56,992	范长老	INFO	====> Epoch: 20