配音擅长领域: 短视频,有声小说,自媒体
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 12:14:38,733 aiaf.cc �������� INFO {'train': {'log_interval': 100, 'eval_interval': 500, 'seed': 1234, 'epochs': 10, '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': 10, '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 ��������'}, '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 ��������', 'content_module': 'cnhubert', 'save_weight_dir': 'SoVITS_weights_v2', 'name': 'aiaf.cc ��������', 'version': 'v2', 'pretrain': None, 'resume_step': None}
2024-08-25 12:14:40,379 aiaf.cc �������� INFO loaded pretrained GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2G2333k.pth
2024-08-25 12:14:40,571 aiaf.cc �������� INFO loaded pretrained GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2D2333k.pth
2024-08-25 12:15:16,209 aiaf.cc �������� INFO Train Epoch: 1 [0%]
2024-08-25 12:15:16,209 aiaf.cc �������� INFO [2.723710536956787, 1.6712019443511963, 5.1970977783203125, 17.87605857849121, 0.0, 1.405948281288147, 0, 9.99875e-05]
2024-08-25 12:16:14,675 aiaf.cc �������� INFO ====> Epoch: 1
2024-08-25 12:16:25,323 aiaf.cc �������� INFO Train Epoch: 2 [15%]
2024-08-25 12:16:25,323 aiaf.cc �������� INFO [2.5834553241729736, 2.249933958053589, 6.728227138519287, 18.658456802368164, 0.0, 1.3969273567199707, 100, 9.99750015625e-05]
2024-08-25 12:17:10,275 aiaf.cc �������� INFO ====> Epoch: 2
2024-08-25 12:17:28,916 aiaf.cc �������� INFO Train Epoch: 3 [30%]
2024-08-25 12:17:28,917 aiaf.cc �������� INFO [2.459381341934204, 2.899250030517578, 8.064023971557617, 19.20619010925293, 0.0, 1.441001296043396, 200, 9.996250468730469e-05]
2024-08-25 12:18:05,168 aiaf.cc �������� INFO ====> Epoch: 3
2024-08-25 12:18:31,656 aiaf.cc �������� INFO Train Epoch: 4 [45%]
2024-08-25 12:18:31,656 aiaf.cc �������� INFO [2.401650905609131, 2.3996782302856445, 6.7357497215271, 19.75629425048828, 0.0, 1.7024040222167969, 300, 9.995000937421877e-05]
2024-08-25 12:19:00,133 aiaf.cc �������� INFO ====> Epoch: 4
2024-08-25 12:19:34,626 aiaf.cc �������� INFO Train Epoch: 5 [60%]
2024-08-25 12:19:34,626 aiaf.cc �������� INFO [2.6448922157287598, 2.4245033264160156, 7.632748126983643, 18.479612350463867, 0.0, 1.36986243724823, 400, 9.993751562304699e-05]
2024-08-25 12:19:55,219 aiaf.cc �������� INFO ====> Epoch: 5
2024-08-25 12:20:37,339 aiaf.cc �������� INFO Train Epoch: 6 [75%]
2024-08-25 12:20:37,339 aiaf.cc �������� INFO [2.6319169998168945, 2.1324031352996826, 5.640797138214111, 15.751457214355469, 0.0, 1.446532964706421, 500, 9.99250234335941e-05]
2024-08-25 12:20:50,032 aiaf.cc �������� INFO ====> Epoch: 6
2024-08-25 12:21:39,935 aiaf.cc �������� INFO Train Epoch: 7 [90%]
2024-08-25 12:21:39,935 aiaf.cc �������� INFO [2.5994725227355957, 2.418424606323242, 6.97303581237793, 17.996950149536133, 0.0, 1.5832817554473877, 600, 9.991253280566489e-05]
2024-08-25 12:21:45,016 aiaf.cc �������� INFO ====> Epoch: 7
2024-08-25 12:22:39,681 aiaf.cc �������� INFO ====> Epoch: 8
2024-08-25 12:22:44,521 aiaf.cc �������� INFO Train Epoch: 9 [5%]
2024-08-25 12:22:44,522 aiaf.cc �������� INFO [2.5789852142333984, 2.1700894832611084, 5.147499084472656, 15.016023635864258, 0.0, 1.600712776184082, 700, 9.98875562335968e-05]
2024-08-25 12:23:34,819 aiaf.cc �������� INFO ====> Epoch: 9
2024-08-25 12:23:47,759 aiaf.cc �������� INFO Train Epoch: 10 [20%]
2024-08-25 12:23:47,761 aiaf.cc �������� INFO [2.6149682998657227, 2.213043451309204, 5.762734889984131, 17.360414505004883, 0.0, 1.6537731885910034, 800, 9.987507028906759e-05]
2024-08-25 12:24:29,757 aiaf.cc �������� INFO Saving model and optimizer state at iteration 10 to logs/aiaf.cc ��������/logs_s2\G_233333333333.pth
2024-08-25 12:24:30,524 aiaf.cc �������� INFO Saving model and optimizer state at iteration 10 to logs/aiaf.cc ��������/logs_s2\D_233333333333.pth
2024-08-25 12:24:32,108 aiaf.cc �������� INFO saving ckpt aiaf.cc ��������_e10:Success.
2024-08-25 12:24:32,109 aiaf.cc �������� INFO ====> Epoch: 10
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