运行实时变声报错了，不闪退也不推理

[daycold1000]

以下是报错日志，从启动推理到停止推理的全部日志

input device:1:麦克风 (Realtek(R) Audio) (MME) output device:8:扬声器 (Realtek(R) Audio) (MME) {'hubert_path': 'hubert_base.pt', 'pth_path': 'C:/RVC-beta/weights/nahida.pth', 'index_path': 'C:/RVC-beta/logs/nahida/trained_IVF742_Flat_nprobe_1_v2.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 gin_channels: 256 self.spk_embed_dim: 109 Traceback (most recent call last): File "C:\RVC-beta\gui.py", line 64, in init print(self.net_g.load_state_dict(cpt["weight"], strict=False)) File "C:\RVC-beta\runtime\lib\site-packages\torch\nn\modules\module.py", line 2041, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for SynthesizerTrnMs256NSFsid: size mismatch for enc_p.emb_phone.weight: copying a param with shape torch.Size([192, 768]) from checkpoint, the shape in current model is torch.Size([192, 256]).

input_wav:(50362,) Audio block passed. Exception ignored from cffi callback <function _StreamBase.init..callback_ptr at 0x0000017A5B5E33A0>: Traceback (most recent call last): File "C:\RVC-beta\runtime\lib\site-packages\sounddevice.py", line 886, in callback_ptr return _wrap_callback( File "C:\RVC-beta\runtime\lib\site-packages\sounddevice.py", line 2687, in wrap_callback callback(*args) File "C:\RVC-beta\gui.py", line 467, in audio_callback self.rvc.infer(self.resampler1(torch.from_numpy(self.input_wav))) File "C:\RVC-beta\gui.py", line 133, in infer score, ix = self.index.search(npy, k=8) File "C:\RVC-beta\runtime\lib\site-packages\faiss_init.py", line 341, in replacement_search assert d == self.d AssertionError: Audio block passed. Audio block passed. Audio block passed. Audio block passed. Audio block passed. Audio block passed. Audio block passed. Audio block passed. ENDing VC

[RVC-Boss]

现在gui还没有支持v2模型

[lingchenma]

现在gui还没有支持v2模型

我用的v1 好像也会卡住

[lingchenma]

is_half:True, device:cuda:0 Input device: 37:麦克风阵列 (Realtek HD Audio Mic input) (Windows WDM-KS) Output device: 17:扬声器 (Realtek(R) Audio) (Windows WASAPI) cuda_is_available: True Process Harvest-3: Process Harvest-7: Process Harvest-2: Process Harvest-5: Process Harvest-8: Process Harvest-4: Process Harvest-9: Process Harvest-6: Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap Traceback (most recent call last): File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "multiprocessing\process.py", line 315, in _bootstrap File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "multiprocessing\queues.py", line 102, in get File "multiprocessing\queues.py", line 103, in get File "multiprocessing\synchronize.py", line 95, in enter File "multiprocessing\connection.py", line 221, in recv_bytes KeyboardInterrupt File "multiprocessing\connection.py", line 310, in _recv_bytes KeyboardInterrupt Traceback (most recent call last): Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py", line 315, in _bootstrap Traceback (most recent call last): File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap Traceback (most recent call last): Traceback (most recent call last): File "multiprocessing\queues.py", line 102, in get File "multiprocessing\queues.py", line 102, in get File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\synchronize.py", line 95, in enter File "multiprocessing\synchronize.py", line 95, in enter KeyboardInterrupt File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "H:\Downloads\Compressed\RVC1006Nvidia\RVC1006Nvidia\gui_v1.py", line 36, in run idx, x, res_f0, n_cpu, ts = self.inp_q.get() File "multiprocessing\queues.py", line 102, in get KeyboardInterrupt File "multiprocessing\queues.py", line 102, in get File "multiprocessing\synchronize.py", line 95, in enter File "multiprocessing\queues.py", line 102, in get File "multiprocessing\queues.py", line 102, in get File "multiprocessing\synchronize.py", line 95, in enter KeyboardInterrupt File "multiprocessing\synchronize.py", line 95, in enter File "multiprocessing\synchronize.py", line 95, in enter KeyboardInterrupt KeyboardInterrupt KeyboardInterrupt ^C终止批处理操作吗(Y/N)? y

[lingchenma]

点击 开始音频转换 后会断到这里，

[github-actions[bot]]

This issue was closed because it has been inactive for 15 days since being marked as stale.