配音擅长领域: 有声小说,情感,影视,温柔细腻,自然动听,读书
模型配音效果
鉴于GPT-SOVITS模型自回归特性,即其配音情绪高度依赖于所提供的参考音频,特此说明:本视频所展示的配音情绪仅为采用某一特定参考音频时的效果示例,并不全面反映GPT-SOVITS模型能够生成的全部情绪范围及最终配音质量的上限。模型的最终表现将随着不同参考音频的输入而展现出多样化。
模型下载
训练日志
2024-08-25 14:22:46,888 aiaf.cc 说书男声1 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/gsv-v2final-pretrained/s2G2333k.pth', 'pretrained_s2D': 'GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2D2333k.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/aiaf.cc 说书男声1'}, '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, 'version': 'v2'}, 's2_ckpt_dir': 'logs/aiaf.cc 说书男声1', 'content_module': 'cnhubert', 'save_weight_dir': 'SoVITS_weights_v2', 'name': 'aiaf.cc 说书男声1', 'version': 'v2', 'pretrain': None, 'resume_step': None}
2024-08-25 14:22:48,193 aiaf.cc 说书男声1 INFO loaded pretrained GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2G2333k.pth
2024-08-25 14:22:48,407 aiaf.cc 说书男声1 INFO loaded pretrained GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2D2333k.pth
2024-08-25 14:23:20,818 aiaf.cc 说书男声1 INFO Train Epoch: 1 [0%]
2024-08-25 14:23:20,818 aiaf.cc 说书男声1 INFO [3.439438581466675, 1.6033985614776611, 14.134965896606445, 21.537893295288086, 0.0, 3.3075194358825684, 0, 9.99875e-05]
2024-08-25 14:23:40,306 aiaf.cc 说书男声1 INFO ====> Epoch: 1
2024-08-25 14:23:59,038 aiaf.cc 说书男声1 INFO ====> Epoch: 2
2024-08-25 14:24:17,042 aiaf.cc 说书男声1 INFO ====> Epoch: 3
2024-08-25 14:24:34,764 aiaf.cc 说书男声1 INFO ====> Epoch: 4
2024-08-25 14:24:36,952 aiaf.cc 说书男声1 INFO Train Epoch: 5 [0%]
2024-08-25 14:24:36,953 aiaf.cc 说书男声1 INFO [2.6226613521575928, 2.2324018478393555, 12.074519157409668, 20.380876541137695, 0.0, 1.8452099561691284, 100, 9.993751562304699e-05]
2024-08-25 14:24:53,025 aiaf.cc 说书男声1 INFO ====> Epoch: 5
2024-08-25 14:25:11,617 aiaf.cc 说书男声1 INFO ====> Epoch: 6
2024-08-25 14:25:29,838 aiaf.cc 说书男声1 INFO ====> Epoch: 7
2024-08-25 14:25:46,847 aiaf.cc 说书男声1 INFO ====> Epoch: 8
2024-08-25 14:25:48,986 aiaf.cc 说书男声1 INFO Train Epoch: 9 [0%]
2024-08-25 14:25:48,987 aiaf.cc 说书男声1 INFO [2.592017889022827, 2.3281939029693604, 12.867263793945312, 20.126373291015625, 0.0, 1.8459186553955078, 200, 9.98875562335968e-05]
2024-08-25 14:26:04,229 aiaf.cc 说书男声1 INFO ====> Epoch: 9
2024-08-25 14:26:20,873 aiaf.cc 说书男声1 INFO ====> Epoch: 10
2024-08-25 14:26:37,571 aiaf.cc 说书男声1 INFO ====> Epoch: 11
2024-08-25 14:26:54,536 aiaf.cc 说书男声1 INFO ====> Epoch: 12
2024-08-25 14:26:56,438 aiaf.cc 说书男声1 INFO Train Epoch: 13 [0%]
2024-08-25 14:26:56,438 aiaf.cc 说书男声1 INFO [2.6428818702697754, 2.0087122917175293, 9.280596733093262, 18.9034366607666, 0.0, 1.617427945137024, 300, 9.983762181915804e-05]
2024-08-25 14:27:11,770 aiaf.cc 说书男声1 INFO ====> Epoch: 13
2024-08-25 14:27:28,365 aiaf.cc 说书男声1 INFO ====> Epoch: 14
2024-08-25 14:27:45,039 aiaf.cc 说书男声1 INFO ====> Epoch: 15
2024-08-25 14:28:01,966 aiaf.cc 说书男声1 INFO ====> Epoch: 16
2024-08-25 14:28:03,930 aiaf.cc 说书男声1 INFO Train Epoch: 17 [0%]
2024-08-25 14:28:03,930 aiaf.cc 说书男声1 INFO [2.632266044616699, 2.5042407512664795, 10.425426483154297, 19.70532989501953, 0.0, 1.5829545259475708, 400, 9.978771236724554e-05]
2024-08-25 14:28:19,115 aiaf.cc 说书男声1 INFO ====> Epoch: 17
2024-08-25 14:28:35,842 aiaf.cc 说书男声1 INFO ====> Epoch: 18
2024-08-25 14:28:52,482 aiaf.cc 说书男声1 INFO ====> Epoch: 19
2024-08-25 14:29:09,137 aiaf.cc 说书男声1 INFO Saving model and optimizer state at iteration 20 to logs/aiaf.cc 说书男声1/logs_s2\G_233333333333.pth
2024-08-25 14:29:09,905 aiaf.cc 说书男声1 INFO Saving model and optimizer state at iteration 20 to logs/aiaf.cc 说书男声1/logs_s2\D_233333333333.pth
2024-08-25 14:29:11,647 aiaf.cc 说书男声1 INFO saving ckpt aiaf.cc 说书男声1_e20:Success.
2024-08-25 14:29:11,647 aiaf.cc 说书男声1 INFO ====> Epoch: 20
如何使用配音模型
1,gpt-sovits模型本地部署(适合有显卡的用户)
2,gpt-sovits模型云端部署
https://aiaf.cc/gpt-sovits-yunduan/
如果您想一对一远程教学模型安装、模型训练,请联系微信 xiaoming1870
声音版权使用声明
本网站所展示的AI声音模型,源自站长及AI模型工作室的精心创作与提供。我们秉持非商业性使用的原则,仅以此平台作为娱乐非商业使用,同时,我们高度重视并严格遵守版权所有者的合法权益。特此声明,我们未获得亦不声称拥有这些声音模型的任何直接使用权或授权。
对于因模型整理、发布、声音转换效果制作及视频教学制作而产生的相关费用,我们明确其仅覆盖上述服务成本,绝不包含对模型版权本身的任何收费。我们承诺,所有活动均在法律框架内进行,尊重版权,合理且合法地使用与分享这些宝贵的AI声音资源。
若您对上述模型或我们的服务存在任何疑问、需要进一步的版权信息,或是有任何宝贵的建议与反馈,我们诚挚邀请您随时与我们取得联系。我们期待与您共同探讨,促进AI声音艺术的健康发展与尊重版权的良好氛围。
重要提示:在利用AI声音模型进行任何活动之前,我们强烈建议您深入了解并遵守相关版权与知识产权法律法规,确保您的行为合法且合规,共同维护良好的创作生态。
请登录后查看评论内容