GPT-SOVITS模型 微软 azure 晓晨声音模型
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
模型训练日志
2024-07-24 12:17:55,600 xiaochen 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/xiaochen'}, '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/xiaochen', 'content_module': 'cnhubert', 'save_weight_dir': 'SoVITS_weights', 'name': 'xiaochen', 'pretrain': None, 'resume_step': None}
2024-07-24 12:17:57,127 xiaochen INFO loaded pretrained GPT_SoVITS/pretrained_models/s2G488k.pth
2024-07-24 12:17:57,336 xiaochen INFO loaded pretrained GPT_SoVITS/pretrained_models/s2D488k.pth
2024-07-24 12:18:29,312 xiaochen INFO Train Epoch: 1 [0%]
2024-07-24 12:18:29,313 xiaochen INFO [2.8378677368164062, 1.877305030822754, 11.843710899353027, 18.460004806518555, 0.0, 1.7773140668869019, 0, 9.99875e-05]
2024-07-24 12:18:44,433 xiaochen INFO ====> Epoch: 1
2024-07-24 12:18:58,345 xiaochen INFO ====> Epoch: 2
2024-07-24 12:19:11,447 xiaochen INFO ====> Epoch: 3
2024-07-24 12:19:24,624 xiaochen INFO ====> Epoch: 4
2024-07-24 12:19:37,623 xiaochen INFO ====> Epoch: 5
2024-07-24 12:19:42,863 xiaochen INFO Train Epoch: 6 [26%]
2024-07-24 12:19:42,864 xiaochen INFO [2.898564338684082, 1.9539498090744019, 10.601505279541016, 14.936346054077148, 0.0, 1.3184711933135986, 100, 9.99250234335941e-05]
2024-07-24 12:19:51,176 xiaochen INFO ====> Epoch: 6
2024-07-24 12:20:04,383 xiaochen INFO ====> Epoch: 7
2024-07-24 12:20:17,453 xiaochen INFO ====> Epoch: 8
2024-07-24 12:20:30,578 xiaochen INFO ====> Epoch: 9
2024-07-24 12:20:43,664 xiaochen INFO ====> Epoch: 10
2024-07-24 12:20:51,724 xiaochen INFO Train Epoch: 11 [53%]
2024-07-24 12:20:51,724 xiaochen INFO [2.9414026737213135, 1.9060834646224976, 12.477777481079102, 16.79501724243164, 0.0, 1.3030052185058594, 200, 9.986258590528146e-05]
2024-07-24 12:20:57,145 xiaochen INFO ====> Epoch: 11
2024-07-24 12:21:10,073 xiaochen INFO ====> Epoch: 12
2024-07-24 12:21:23,008 xiaochen INFO ====> Epoch: 13
2024-07-24 12:21:35,927 xiaochen INFO ====> Epoch: 14
2024-07-24 12:21:49,032 xiaochen INFO ====> Epoch: 15
2024-07-24 12:22:00,284 xiaochen INFO Train Epoch: 16 [79%]
2024-07-24 12:22:00,284 xiaochen INFO [2.6509132385253906, 2.086803674697876, 12.517009735107422, 17.605146408081055, 0.0, 1.5448822975158691, 300, 9.980018739066937e-05]
2024-07-24 12:22:02,492 xiaochen INFO ====> Epoch: 16
2024-07-24 12:22:15,650 xiaochen INFO ====> Epoch: 17
2024-07-24 12:22:29,068 xiaochen INFO ====> Epoch: 18
2024-07-24 12:22:42,137 xiaochen INFO ====> Epoch: 19
2024-07-24 12:22:55,045 xiaochen INFO Saving model and optimizer state at iteration 20 to logs/xiaochen/logs_s2\G_233333333333.pth
2024-07-24 12:22:55,867 xiaochen INFO Saving model and optimizer state at iteration 20 to logs/xiaochen/logs_s2\D_233333333333.pth
2024-07-24 12:22:57,572 xiaochen INFO saving ckpt xiaochen_e20:Success.
2024-07-24 12:22:57,573 xiaochen INFO ====> Epoch: 20如何使用配音模型
1，gpt-sovits模型云端部署
https://aiaf.cc/gpt-sovits-yunduan/.html
2，gpt-sovits模型本地部署
https://aiaf.cc/gpt-sovits/.html
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
本网站展示的 AI 声音模型由站长及工作室精心创作并提供。遵循非商业性使用原则，仅作娱乐用途，重视并遵守版权所有者权益，未获授权也不声称拥有使用权。模型整理等产生的费用仅覆盖服务成本，不涉及版权收费。所有活动在法律框架内进行，尊重版权、合法使用分享。如有疑问、需版权信息或建议反馈，可随时联系，共同促进 AI 声音艺术发展与营造尊重版权氛围。
没有回复内容