GPT-SOVITS模型|悬疑电影解说模型男声 悬疑解说配音模型
炼丹师永久会员 298，全站配音模型免费下载，模型持续更新
高级炼丹师免费训练1个配音模型
声音特点适用领域：电影解说，科普，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
2024-08-15 18:36:31,788 peiyin.me 故事男声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/peiyin.me 故事男声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/peiyin.me 故事男声1', 'content_module': 'cnhubert', 'save_weight_dir': 'SoVITS_weights_v2', 'name': 'peiyin.me 故事男声1', 'version': 'v2', 'pretrain': None, 'resume_step': None}
2024-08-15 18:36:33,107 peiyin.me 故事男声1 INFO loaded pretrained GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2G2333k.pth
2024-08-15 18:36:33,325 peiyin.me 故事男声1 INFO loaded pretrained GPT_SoVITS/pretrained_models/gsv-v2final-pretrained/s2D2333k.pth
2024-08-15 18:37:03,892 peiyin.me 故事男声1 INFO Train Epoch: 1 [0%]
2024-08-15 18:37:03,893 peiyin.me 故事男声1 INFO [2.912601947784424, 1.7173140048980713, 6.823921203613281, 13.761653900146484, 0.0, 2.032060146331787, 0, 9.99875e-05]
2024-08-15 18:37:24,064 peiyin.me 故事男声1 INFO ====> Epoch: 1
2024-08-15 18:37:43,360 peiyin.me 故事男声1 INFO ====> Epoch: 2
2024-08-15 18:38:02,336 peiyin.me 故事男声1 INFO ====> Epoch: 3
2024-08-15 18:38:16,933 peiyin.me 故事男声1 INFO Train Epoch: 4 [70%]
2024-08-15 18:38:16,934 peiyin.me 故事男声1 INFO [2.6834359169006348, 2.310040235519409, 9.991488456726074, 16.04734230041504, 0.0, 1.6837549209594727, 100, 9.995000937421877e-05]
2024-08-15 18:38:21,542 peiyin.me 故事男声1 INFO ====> Epoch: 4
2024-08-15 18:38:40,242 peiyin.me 故事男声1 INFO ====> Epoch: 5
2024-08-15 18:38:58,964 peiyin.me 故事男声1 INFO ====> Epoch: 6
2024-08-15 18:39:17,956 peiyin.me 故事男声1 INFO ====> Epoch: 7
2024-08-15 18:39:27,488 peiyin.me 故事男声1 INFO Train Epoch: 8 [41%]
2024-08-15 18:39:27,489 peiyin.me 故事男声1 INFO [2.688433885574341, 2.244929552078247, 11.27292251586914, 18.487770080566406, 0.0, 1.386842131614685, 200, 9.990004373906418e-05]
2024-08-15 18:39:37,030 peiyin.me 故事男声1 INFO ====> Epoch: 8
2024-08-15 18:39:55,678 peiyin.me 故事男声1 INFO ====> Epoch: 9
2024-08-15 18:40:14,408 peiyin.me 故事男声1 INFO ====> Epoch: 10
2024-08-15 18:40:33,219 peiyin.me 故事男声1 INFO ====> Epoch: 11
2024-08-15 18:40:37,531 peiyin.me 故事男声1 INFO Train Epoch: 12 [11%]
2024-08-15 18:40:37,531 peiyin.me 故事男声1 INFO [2.6222426891326904, 2.3922576904296875, 11.573132514953613, 19.36470603942871, 0.0, 1.3982831239700317, 300, 9.98501030820433e-05]
2024-08-15 18:40:52,456 peiyin.me 故事男声1 INFO ====> Epoch: 12
2024-08-15 18:41:11,267 peiyin.me 故事男声1 INFO ====> Epoch: 13
2024-08-15 18:41:30,021 peiyin.me 故事男声1 INFO ====> Epoch: 14
2024-08-15 18:41:46,418 peiyin.me 故事男声1 INFO Train Epoch: 15 [81%]
2024-08-15 18:41:46,418 peiyin.me 故事男声1 INFO [2.6851561069488525, 2.2251508235931396, 11.629902839660645, 18.04998016357422, 0.0, 1.500746250152588, 400, 9.981266397366609e-05]
2024-08-15 18:41:49,276 peiyin.me 故事男声1 INFO ====> Epoch: 15
2024-08-15 18:42:08,392 peiyin.me 故事男声1 INFO ====> Epoch: 16
2024-08-15 18:42:27,549 peiyin.me 故事男声1 INFO ====> Epoch: 17
2024-08-15 18:42:46,389 peiyin.me 故事男声1 INFO ====> Epoch: 18
2024-08-15 18:42:57,873 peiyin.me 故事男声1 INFO Train Epoch: 19 [52%]
2024-08-15 18:42:57,873 peiyin.me 故事男声1 INFO [2.694093704223633, 1.9746001958847046, 6.611715793609619, 12.423184394836426, 0.0, 1.3608942031860352, 500, 9.976276699833672e-05]
2024-08-15 18:43:05,669 peiyin.me 故事男声1 INFO ====> Epoch: 19
2024-08-15 18:43:24,347 peiyin.me 故事男声1 INFO Saving model and optimizer state at iteration 20 to logs/peiyin.me 故事男声1/logs_s2\G_233333333333.pth
2024-08-15 18:43:25,250 peiyin.me 故事男声1 INFO Saving model and optimizer state at iteration 20 to logs/peiyin.me 故事男声1/logs_s2\D_233333333333.pth
2024-08-15 18:43:26,763 peiyin.me 故事男声1 INFO saving ckpt peiyin.me 故事男声1_e20:Success.
2024-08-15 18:43:26,763 peiyin.me 故事男声1 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