Retrieval-based-Voice-Conversion-WebUI icon indicating copy to clipboard operation
Retrieval-based-Voice-Conversion-WebUI copied to clipboard

After training the model with one-click training, run go-realtime-gui.bat, and the program exits when you click Start Audio Conversion.

Open wulusai2333 opened this issue 2 years ago • 2 comments

使用一键训练训练好了模型,运行go-realtime-gui.bat,配置好了,点击开始音频转换时程序退出 模型训练采样率为默认的40k和48k,使用的显卡NVIDIA GeForce RTX 3090,填好输入训练文件夹路径使用一键训练,其他配置没有变动 D:\project\RVC-beta\RVC-beta-v2-0528>runtime\python.exe gui.py input device:1:麦克风 (HUAWEI USB-C HEADSET) (MME) output device:5:Realtek Digital Output (Realtek (MME) {'hubert_path': 'hubert_base.pt', 'pth_path': 'logs\\ganyu48\\G_2220.pth', 'index_path': 'logs\\ganyu48\\added_IVF3435_Flat_nprobe_1_ganyu48_v1.index', 'npy_path': "你不需要填写这个You don't need write this.", 'pitch': 12.0, 'samplerate': 44100, 'block_time': 1.0, 'buffer_num': 1, 'threhold': -30.0, 'crossfade_time': 0.08, 'extra_time': 0.05, 'I_noise_reduce': False, 'O_noise_reduce': False, 'index_rate': 0.5} using_cuda:True index search enabled load model(s) from hubert_base.pt Traceback (most recent call last): File "D:\project\RVC-beta\RVC-beta-v2-0528\gui.py", line 79, in __init__ self.tgt_sr = cpt["config"][-1] KeyError: 'config'

wulusai2333 avatar Jun 13 '23 13:06 wulusai2333

选错模型了,在weights下头找

RVC-Boss avatar Jun 13 '23 14:06 RVC-Boss

非常感谢,已经解决了 @RVC-Boss

wulusai2333 avatar Jun 14 '23 06:06 wulusai2333