Open Rakkyotan opened 1 month ago
please show me more log.
2024-07-27 17:13:07,028 - vcclient - gpu_device_manager - INFO - Reloading GPU info - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 120 2024-07-27 17:13:07,069 - vcclient - gpu_device_manager - ERROR - Failed to reload_gpu_info_for_win. Failed to resolve Python.Runtime.Loader.Initialize from C:\RVC2045_internal\pythonnet\runtime\Python.Runtime.dll. If you are using torch_cuda, this error can be ignored. - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 50 2024-07-27 17:13:07,069 - vcclient - gpu_device_manager - INFO - GPU[sys]:[GPUInfo(name='cpu', device_id='-1', adapter_ram=0, device_id_int=-1, cuda_compute_version_major=-1, cuda_compute_version_minor=-1)] - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 123 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - Sat Jul 27 17:13:07 2024 - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - +-----------------------------------------------------------------------------------------+ - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | NVIDIA-SMI 560.70 Driver Version: 560.70 CUDA Version: 12.6 | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - |-----------------------------------------+------------------------+----------------------+ - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | GPU Name Driver-Model | Bus-Id Disp.A | Volatile Uncorr. ECC | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | | | MIG M. | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - |=========================================+========================+======================| - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0 NVIDIA GeForce RTX 4070 Ti WDDM | 00000000:01:00.0 On | N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0% 47C P3 19W / 285W | 1624MiB / 12282MiB | 9% Default | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | | | N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - +-----------------------------------------+------------------------+----------------------+ - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - +-----------------------------------------------------------------------------------------+ - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | Processes: | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | GPU GI CI PID Type Process name GPU Memory | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | ID ID Usage | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - |=========================================================================================| - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 2460 C+G ...al\Discord\app-1.0.9155\Discord.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 5556 C+G ...crosoft\Edge\Application\msedge.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 5608 C+G C:\Windows\explorer.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 7556 C+G ...mpt_builder\LogiAiPromptBuilder.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,183 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 9312 C+G ...tionsPlus\logioptionsplus_agent.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 10536 C+G ...nt.CBS_cw5n1h2txyewy\SearchHost.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 10564 C+G ...2txyewy\StartMenuExperienceHost.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 13432 C+G ...GeForce Experience\NVIDIA Share.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 15952 C+G ...n\126.0.2592.113\msedgewebview2.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 17188 C+G ...5n1h2txyewy\ShellExperienceHost.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 17612 C+G ...GeForce Experience\NVIDIA Share.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 17772 C+G ...CBS_cw5n1h2txyewy\TextInputHost.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 18384 C+G ...ekyb3d8bbwe\PhoneExperienceHost.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 22472 C+G ...oogle\Chrome\Application\chrome.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 24152 C+G ...les\Microsoft OneDrive\OneDrive.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 26824 C+G ...siveControlPanel\SystemSettings.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 28952 C+G ...aam7r\AcrobatNotificationClient.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 29164 C+G ...ative\Creative App\Creative.App.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 29416 C+G ...\cef\cef.win7x64\steamwebhelper.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 29656 C+G ...\cef\cef.win7x64\steamwebhelper.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 30100 C+G ...ejd91yc\AdobeNotificationClient.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 30208 C+G ...n\126.0.2592.113\msedgewebview2.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 30608 C+G ...on\HEX\Creative Cloud UI Helper.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 30648 C+G ...pdnekdrzrea0\XboxGameBarSpotify.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - | 0 N/A N/A 34400 C+G ...__8wekyb3d8bbwe\WindowsTerminal.exe N/A | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - +-----------------------------------------------------------------------------------------+ - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,184 - vcclient - gpu_device_manager - INFO - - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 96 2024-07-27 17:13:07,185 - vcclient - gpu_device_manager - INFO - GPUcuda: available:True, num:1, mps_enabled: False - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 132 2024-07-27 17:13:07,185 - vcclient - gpu_device_manager - INFO - GPUcuda: cuda_version(build):12.1, cudnn_version(build)8907 - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 133 2024-07-27 17:13:07,185 - vcclient - gpu_device_manager - INFO - GPUcuda: cuda_driver_version:12.6 | - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 134 2024-07-27 17:13:07,185 - vcclient - gpu_device_manager - INFO - GPUcuda: [GPUInfo(name='cpu', device_id='-1', adapter_ram=0, device_id_int=-1, cuda_compute_version_major=-1, cuda_compute_version_minor=-1), GPUInfo(name='NVIDIA GeForce RTX 4070 Ti', device_id='0', adapter_ram=12878086144, device_id_int=0, cuda_compute_version_major=8, cuda_compute_version_minor=9)] - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 135 2024-07-27 17:13:07,185 - vcclient - audio_device_manager - INFO - Reloading Audio Device info - vcclient_dev\voice_changer\auido_device_manager\audio_device_manager.py - 132 2024-07-27 17:13:08,947 - vcclient - audio_device_manager - INFO - Audio(input):[AudioDevice(kind='audioinput', index=0, name='Microsoft サウンド マッパー - Input', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=1, name='Line (Yamaha AG03MK2)', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=2, name='Voicemeeter Out A3 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=3, name='Voicemeeter Out A5 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=4, name='Voicemeeter Out A4 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=5, name='CABLE Output (VB-Audio Virtual ', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=6, name='Voicemeeter Out A1 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=7, name='Voicemeeter Out A2 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=8, name='ライン (Yamaha SYNCROOM Driver (WD', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=9, name='Voicemeeter Out B3 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=10, name='Voicemeeter Out B1 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=11, name='Voicemeeter Out B2 (VB-Audio Vo', host_api='MME', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=27, name='プライマリ サウンド キャプチャ ドライバー', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=28, name='Line (Yamaha AG03MK2)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=29, name='Voicemeeter Out A3 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=30, name='Voicemeeter Out A5 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=31, name='Voicemeeter Out A4 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=32, name='CABLE Output (VB-Audio Virtual Cable)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=33, name='Voicemeeter Out A1 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=34, name='Voicemeeter Out A2 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=35, name='ライン (Yamaha SYNCROOM Driver (WDM))', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=36, name='Voicemeeter Out B3 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=37, name='Voicemeeter Out B1 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=38, name='Voicemeeter Out B2 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=53, name='Creative SB USB RT ASIO', host_api='ASIO', max_input_channels=2, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=54, name='Generic Low Latency ASIO Driver', host_api='ASIO', max_input_channels=2, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=55, name='Realtek ASIO', host_api='ASIO', max_input_channels=2, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=56, name='Voicemeeter AUX Virtual ASIO', host_api='ASIO', max_input_channels=8, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=57, name='Voicemeeter Insert Virtual ASIO', host_api='ASIO', max_input_channels=22, max_output_channels=22, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=58, name='Voicemeeter Virtual ASIO', host_api='ASIO', max_input_channels=8, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=59, name='Yamaha Steinberg USB ASIO', host_api='ASIO', max_input_channels=2, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=74, name='Voicemeeter Out A3 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=75, name='Voicemeeter Out A5 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=76, name='Voicemeeter Out A4 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=77, name='CABLE Output (VB-Audio Virtual Cable)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=78, name='Voicemeeter Out A1 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=79, name='Voicemeeter Out A2 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=80, name='ライン (Yamaha SYNCROOM Driver (WDM))', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=81, name='Voicemeeter Out B3 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=82, name='Voicemeeter Out B1 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=83, name='Line (Yamaha AG03MK2)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=84, name='Voicemeeter Out B2 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=86, name='Input (Voicemeeter Point 3)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=88, name='Input (Voicemeeter Point 6)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=89, name='Voicemeeter Out 1 (Voicemeeter Point 1)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=90, name='Voicemeeter Out 4 (Voicemeeter Point 4)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=91, name='Voicemeeter Out 7 (Voicemeeter Point 7)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=93, name='Input (Voicemeeter Point 1)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=95, name='Input (Voicemeeter Point 4)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=97, name='Input (Voicemeeter Point 7)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=98, name='Voicemeeter Out 2 (Voicemeeter Point 2)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=99, name='Voicemeeter Out 5 (Voicemeeter Point 5)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=100, name='Voicemeeter Out 8 (Voicemeeter Point 8)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=102, name='Input (Voicemeeter Point 2)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=104, name='Input (Voicemeeter Point 5)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=106, name='Input (Voicemeeter Point 8)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=107, name='Voicemeeter Out 3 (Voicemeeter Point 3)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=108, name='Voicemeeter Out 6 (Voicemeeter Point 6)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=110, name='マイク (Sound Blaster X5)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=111, name='再生リダイレクト (Sound Blaster X5)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=112, name='ライン (Sound Blaster X5)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=113, name='SPDIF インターフェイス (Sound Blaster X5)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audioinput', index=117, name='ライン入力 (Realtek HD Audio Line input)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=118, name='マイク (Realtek HD Audio Mic input)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=120, name='ステレオ ミキサー (Realtek HD Audio Stereo input)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=121, name='Line (Yamaha AG03MK2-1)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=123, name='CABLE Output (VB-Audio Point)', host_api='Windows WDM-KS', max_input_channels=8, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=125, name='ライン (DUETTO Wave)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audioinput', index=127, name='マイク (C922 Pro Stream Webcam)', host_api='Windows WDM-KS', max_input_channels=2, max_output_channels=0, default_samplerate=32000, available_samplerates=[])] - vcclient_dev\voice_changer\auido_device_manager\audio_device_manager.py - 134 2024-07-27 17:13:08,948 - vcclient - audio_device_manager - INFO - Audio(output):[AudioDevice(kind='audiooutput', index=12, name='Microsoft サウンド マッパー - Output', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=13, name='スピーカー (Sound Blaster X5)', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=14, name='ライン (Yamaha SYNCROOM Driver (WD', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=15, name='Voicemeeter In 5 (VB-Audio Voic', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=16, name='スピーカー (Realtek(R) Audio)', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=17, name='Voicemeeter In 4 (VB-Audio Voic', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=18, name='Voicemeeter In 1 (VB-Audio Voic', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=19, name='Voicemeeter Input (VB-Audio Voi', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=20, name='Voicemeeter VAIO3 Input (VB-Aud', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=21, name='Line (Yamaha AG03MK2)', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=22, name='CABLE Input (VB-Audio Virtual C', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=23, name='Voicemeeter In 3 (VB-Audio Voic', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=24, name='Realtek Digital Output (Realtek', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=25, name='Voicemeeter In 2 (VB-Audio Voic', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=26, name='Voicemeeter AUX Input (VB-Audio', host_api='MME', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=39, name='プライマリ サウンド ドライバー', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=40, name='ライン (Yamaha SYNCROOM Driver (WDM))', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=41, name='Voicemeeter In 5 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=42, name='スピーカー (Realtek(R) Audio)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=43, name='Voicemeeter In 4 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=44, name='Voicemeeter In 1 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=45, name='Voicemeeter Input (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=46, name='Voicemeeter VAIO3 Input (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=47, name='Line (Yamaha AG03MK2)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=48, name='CABLE Input (VB-Audio Virtual Cable)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=49, name='Voicemeeter In 3 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=50, name='Realtek Digital Output (Realtek(R) Audio)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=51, name='Voicemeeter In 2 (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=52, name='Voicemeeter AUX Input (VB-Audio Voicemeeter VAIO)', host_api='Windows DirectSound', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=53, name='Creative SB USB RT ASIO', host_api='ASIO', max_input_channels=2, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=54, name='Generic Low Latency ASIO Driver', host_api='ASIO', max_input_channels=2, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=55, name='Realtek ASIO', host_api='ASIO', max_input_channels=2, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=56, name='Voicemeeter AUX Virtual ASIO', host_api='ASIO', max_input_channels=8, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=57, name='Voicemeeter Insert Virtual ASIO', host_api='ASIO', max_input_channels=22, max_output_channels=22, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=58, name='Voicemeeter Virtual ASIO', host_api='ASIO', max_input_channels=8, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=59, name='Yamaha Steinberg USB ASIO', host_api='ASIO', max_input_channels=2, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=60, name='ライン (Yamaha SYNCROOM Driver (WDM))', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=61, name='Voicemeeter In 5 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=62, name='スピーカー (Realtek(R) Audio)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=63, name='Voicemeeter In 4 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=64, name='Voicemeeter In 1 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=65, name='Voicemeeter Input (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=66, name='スピーカー (Sound Blaster X5)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=384000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=67, name='Voicemeeter VAIO3 Input (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=68, name='Line (Yamaha AG03MK2)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=69, name='CABLE Input (VB-Audio Virtual Cable)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=70, name='Voicemeeter In 3 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=71, name='Realtek Digital Output (Realtek(R) Audio)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=72, name='Voicemeeter In 2 (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=73, name='Voicemeeter AUX Input (VB-Audio Voicemeeter VAIO)', host_api='Windows WASAPI', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=85, name='Output (Voicemeeter Point 3)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=87, name='Output (Voicemeeter Point 6)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=92, name='Output (Voicemeeter Point 1)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=94, name='Output (Voicemeeter Point 4)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=96, name='Output (Voicemeeter Point 7)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=101, name='Output (Voicemeeter Point 2)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=103, name='Output (Voicemeeter Point 5)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=105, name='Output (Voicemeeter Point 8)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=109, name='Speakers (Sound Blaster X5)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=114, name='Output (NVIDIA High Definition Audio)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=115, name='Output (NVIDIA High Definition Audio)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=2, default_samplerate=48000, available_samplerates=[]), AudioDevice(kind='audiooutput', index=116, name='Speakers (Realtek HD Audio output)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=119, name='SPDIF Out (Realtek HDA SPDIF Out)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=122, name='Line (Yamaha AG03MK2-1)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=124, name='Speakers (VB-Audio Point)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=8, default_samplerate=44100, available_samplerates=[]), AudioDevice(kind='audiooutput', index=126, name='Line Out (DUETTO Wave)', host_api='Windows WDM-KS', max_input_channels=0, max_output_channels=2, default_samplerate=44100, available_samplerates=[])] - vcclient_dev\voice_changer\auido_device_manager\audio_device_manager.py - 135 2024-07-27 17:13:08,949 - vcclient - vcserver - INFO - Starting VCServer on port 18000 - vcclient_dev\server\vcserver.py - 107 2024-07-27 17:13:08,956 - vcclient - vcclient_cui - INFO - Starting VCClient CUI - vcclient_dev\cui\vcclient_cui.py - 114 2024-07-27 17:13:08,956 - vcclient - vcclient_cui - INFO - port: 18000, https: False - vcclient_dev\cui\vcclient_cui.py - 115 2024-07-27 17:13:08,965 - vcclient - watchdog - INFO - MyWatcher Started - vcclient_dev\cui\utils\watchdog.py - 40 2024-07-27 17:13:08,986 - vcclient - client_launcher - WARNING - - vcclient_dev\client_launcher\client_launcher.py - 81 2024-07-27 17:13:09,229 - vcclient - client_launcher - WARNING - [VCClient] Access http://localhost:18000/ - vcclient_dev\client_launcher\client_launcher.py - 81 2024-07-27 17:13:09,294 - vcclient - client_launcher - WARNING - [VCClient] wait web server...0 http://localhost:18000/ - vcclient_dev\client_launcher\client_launcher.py - 81 2024-07-27 17:13:10,128 - vcclient - vcserver_socketio - INFO - SocketIOApp Allow Origins None - vcclient_dev\server\vcserver_socketio.py - 87 2024-07-27 17:13:10,128 - uvicorn.er - server - INFO - Started server process [4860] - uvicorn\server.py - 82 2024-07-27 17:13:10,128 - uvicorn.er - on - INFO - Waiting for application startup. - uvicorn\lifespan\on.py - 48 2024-07-27 17:13:10,128 - uvicorn.er - on - INFO - Application startup complete. - uvicorn\lifespan\on.py - 62 2024-07-27 17:13:10,129 - uvicorn.er - server - INFO - Uvicorn running on http://('0.0.0.0',):18000 (Press CTRL+C to quit) - uvicorn\server.py - 214 2024-07-27 17:13:10,249 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52704 - "GET / HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,250 - vcclient - client_launcher - WARNING - [VCClient] wait web server... done 200 - vcclient_dev\client_launcher\client_launcher.py - 81 2024-07-27 17:13:10,588 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET / HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,593 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /index.js HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,608 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /static/chunks/35b9f6d55ab5cc028785.css HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,720 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /assets/i18n/ja/translation.json HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,721 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /assets/i18n/en/translation.json HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,726 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /assets/gui_settings/GUI.json HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,727 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /assets/gui_settings/version.txt HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,727 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /assets/gui_settings/edition.txt HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,734 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/configuration-manager/configuration HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,738 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/audio-device-manager/input_devices HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,742 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/audio-device-manager/output_devices HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,744 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/gpu-device-manager/devices HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,745 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/module-manager/modules HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,748 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/sample-manager/samples HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,755 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/slot-manager/slots HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,757 - vcclient - voice_changer_manage - INFO - Getting voice changer manager information. - vcclient_dev\voice_changer\voice_change_manager\voice_changer_manager.py - 22 2024-07-27 17:13:10,757 - vcclient - voice_changer - INFO - slot_index: -1 -> 8, gpu_device_index: -1 -> 0 - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 86 2024-07-27 17:13:10,757 - vcclient - rvc_pipeline - INFO - construct new pipelinepitch: slot_index:8, gpu_device_id:0 pitch_estimator: fcpe - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 35 2024-07-27 17:13:10,805 - vcclient - device_manager - INFO - GPU num: 1, mps_enabled: False, directml_available: False - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 31 2024-07-27 17:13:10,805 - vcclient - device_manager - INFO - get_pytorch_device: cuda:0 - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 35 2024-07-27 17:13:10,907 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52717 - "GET /assets/icons/github.svg HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,909 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52716 - "GET /api/configuration-manager/configuration HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,910 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52717 - "GET /assets/icons/help-circle.svg HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,910 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52716 - "GET /assets/icons/monitor.svg HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,911 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52717 - "GET /assets/icons/buymeacoffee.png HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:10,924 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52717 - "GET /assets/icons/human.png HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:11,050 - vcclient - device_manager - INFO - available_providers: ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 64 2024-07-27 17:13:11,050 - vcclient - device_manager - INFO - gpu_num: 2, cuda_len: 2, gpu_len: 0 - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 71 2024-07-27 17:13:11,050 - vcclient - device_manager - INFO - gpu_num: 2, cuda_len: 2, gpu_len: 0 - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 72 2024-07-27 17:13:11,050 - vcclient - device_manager - INFO - get_onnx_execution_privider: (['CUDAExecutionProvider'], [{'device_id': 0}]) - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 59 2024-07-27 17:13:11,591 - vcclient - device_manager - INFO - get_pytorch_device: cuda:0 - vcclient_dev\voice_changer\voice_change_manager\device_manager\device_manager.py - 35 2024-07-27 17:13:11,997 - vcclient - voice_changer - INFO - slot_index Changed: 8, gpu_device_index: 0 - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 76 2024-07-27 17:13:11,997 - vcclient - voice_changer - WARNING - Input or output sample rate is not set - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 106 2024-07-27 17:13:11,997 - vcclient - voice_changer - INFO - resample_ratio_in:0.3333333333333333, resample_ratio_out:1.2, resample_ratio_monitor:1.2 - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 121 2024-07-27 17:13:11,997 - vcclient - voice_changer - INFO - self.vc_info.vc_input_sample_rate:16000, self.input_sample_rate:48000 - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 122 2024-07-27 17:13:11,997 - vcclient - voice_changer - INFO - self.vc_info.vc_output_sample_rate:40000, self.output_sample_rate:48000 - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 123 2024-07-27 17:13:11,997 - vcclient - voice_changer - INFO - self.vc_monitor_sample_rate:40000, self.monitor_sample_rate:48000 - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 124 2024-07-27 17:13:11,999 - vcclient - vcserver_rest_api_vo - INFO - get_voice_changer_information local_voice_changer_interface_active=False voice_changer_information=VoiceChangerInformation(slot_index=8, pitch_estimator_type='fcpe', gpu_device_index=0, input_sample_rate=48000, output_sample_rate=48000, monitor_sample_rate=48000, vc_input_sample_rate=16000, vc_output_sample_rate=40000, resample_ratio_in=0.3333333333333333, resample_ratio_out=1.2, resample_ratio_monitor=1.2, resample_ratio_pass_through_in_out=1.0, resample_ratio_pass_through_in_monitor=1.0, enable_high_pass_filter=False, high_pass_filter_cutoff=100.0, enable_low_pass_filter=False, low_pass_filter_cutoff=10000.0, chunk_sec=0.2, pipeline_info=RVCPipelineInfo(slot_index=8, input_sample_rate=16000, output_sample_rate=40000, chunk_sec=0.2, slot_info={'slot_index': 8, 'voice_changer_type': 'RVC', 'name': 'mine_kira', 'description': '', 'credit': '', 'terms_of_use_url': '', 'icon_file': None, 'speakers': {}, 'model_file': WindowsPath('mine_kira.pth'), 'index_file': None, 'is_onnx': False, 'inferencer_type': 'pyTorchRVCv2', 'sample_rate': 40000, 'is_f0': True, 'deprecated': False, 'embedder': 'hubert_base_l12', 'pitch_estimator': 'fcpe', 'sample_id': None, 'version': 'v2', 'chunk_sec': 0.2, 'pitch_shift': 14, 'index_ratio': 0.0, 'protect_ratio': 0.5}, embedder_info=EmbedderInfo(embedder_type='contentvec', model_file=WindowsPath('modules/contentvec/contentvec-f.onnx'), device_id=0, candidate_onnx_providers=['CUDAExecutionProvider'], candidate_onnx_provider_options="[{'device_id': 0}]", onnx_providers=['CUDAExecutionProvider', 'CPUExecutionProvider'], onnx_provider_options="{'CUDAExecutionProvider': {'cudnn_conv_algo_search': 'EXHAUSTIVE', 'device_id': '0', 'has_user_compute_stream': '0', 'cudnn_conv1d_pad_to_nc1d': '0', 'gpu_external_alloc': '0', 'gpu_mem_limit': '18446744073709551615', 'enable_cuda_graph': '0', 'gpu_external_free': '0', 'gpu_external_empty_cache': '0', 'arena_extend_strategy': 'kNextPowerOfTwo', 'do_copy_in_default_stream': '1', 'cudnn_conv_use_max_workspace': '1', 'tunable_op_enable': '0', 'tunable_op_tuning_enable': '0', 'tunable_op_max_tuning_duration_ms': '0', 'enable_skip_layer_norm_strict_mode': '0', 'prefer_nhwc': '0', 'use_ep_level_unified_stream': '0'}, 'CPUExecutionProvider': {}}"), pitch_estimator_info=PitchEstimatorInfo(pitch_estimator_type='fcpe', model_file=None, device_id=0, candidate_onnx_providers=None, candidate_onnx_provider_options=None, onnx_providers=None, onnx_provider_options=None), inferencer_info=RVCInferencerInfo(inferencer_type='pyTorchRVCv2', model_file=WindowsPath('model_dir/8/mine_kira.pth'), device_id=0, candidate_onnx_providers=None, candidate_onnx_provider_options=None, onnx_providers=None, onnx_provider_options=None)), voice_changer_type='RVC', bulk_process_start_flag=False, recording_start_flag=False, monitor_enabled=False) - vcclient_dev\server\vcserver_rest_api_voice_changaer.py - 107 2024-07-27 17:13:12,000 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:52709 - "GET /api/voice-changer-manager/information HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477 2024-07-27 17:13:17,384 - vcclient - voice_changer - WARNING - data type resampled is short. padded.:(3057,), shape:(3200,) - vcclient_dev\voice_changer\voice_change_manager\voice_changer.py - 486 2024-07-27 17:13:17,384 - vcclient - rvc_pipeline - INFO - noise gate 1.8141061377250035e-05 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:17,583 - vcclient - rvc_pipeline - INFO - noise gate 2.118043151848729e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:17,784 - vcclient - rvc_pipeline - INFO - noise gate 2.1579774195716497e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:17,984 - vcclient - rvc_pipeline - INFO - noise gate 2.1851421209458435e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:18,185 - vcclient - rvc_pipeline - INFO - noise gate 2.1647147005145333e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:18,384 - vcclient - rvc_pipeline - INFO - noise gate 2.160158067667661e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:18,584 - vcclient - rvc_pipeline - INFO - noise gate 2.1756402421454924e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:18,783 - vcclient - rvc_pipeline - INFO - noise gate 2.1670391259817354e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:18,984 - vcclient - rvc_pipeline - INFO - noise gate 2.1589397299178536e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:19,183 - vcclient - rvc_pipeline - INFO - noise gate 2.1589922963768136e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:21,184 - vcclient - rvc_pipeline - INFO - noise gate 0.00017701891207009087 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:21,383 - vcclient - rvc_pipeline - INFO - noise gate 2.2957978596047943e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:21,584 - vcclient - rvc_pipeline - INFO - noise gate 2.274769851017799e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:21,784 - vcclient - rvc_pipeline - INFO - noise gate 3.4531825229132753e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:21,984 - vcclient - rvc_pipeline - INFO - noise gate 7.370567917714765e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:22,184 - vcclient - rvc_pipeline - INFO - noise gate 2.9561689772404538e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:22,384 - vcclient - rvc_pipeline - INFO - noise gate 2.2175031451320662e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:22,584 - vcclient - rvc_pipeline - INFO - noise gate 3.4971394436466786e-05 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:22,784 - vcclient - rvc_pipeline - INFO - noise gate 2.2047887914171364e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:22,984 - vcclient - rvc_pipeline - INFO - noise gate 2.1628916043858253e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:23,183 - vcclient - rvc_pipeline - INFO - noise gate 7.679475397284356e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:23,382 - vcclient - rvc_pipeline - INFO - noise gate 2.1661978191545864e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:23,582 - vcclient - rvc_pipeline - INFO - noise gate 2.1687183617978344e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:23,782 - vcclient - rvc_pipeline - INFO - noise gate 3.863153086561867e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:23,983 - vcclient - rvc_pipeline - INFO - noise gate 2.197069586382472e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:24,182 - vcclient - rvc_pipeline - INFO - noise gate 2.1843925488219386e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:24,383 - vcclient - rvc_pipeline - INFO - noise gate 6.463587170281225e-05 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:24,583 - vcclient - rvc_pipeline - INFO - noise gate 2.1806086298114794e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:24,783 - vcclient - rvc_pipeline - INFO - noise gate 2.1900261014123957e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:24,983 - vcclient - rvc_pipeline - INFO - noise gate 2.1670383700853697e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175 2024-07-27 17:13:25,183 - vcclient - rvc_pipeline - INFO - noise gate 2.2035930313008007e-06 < -50.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 175
From startup to voice conversion in a few seconds.
I share this same issue and I was about to report it but I wanted to wait to test properly before submitting the issue. In my case, I compared cpu and gpu usage between v1 and v2, and v2 takes about a 30% of my cpu even when no conversion is being done (software is activated and running but there is no input yet). My friend with AMD CPU and nvidia 3080 have the same issue when she uses rmvpe_onnx on v1. It doesn't happens when she uses rmvpe. I don't have this issue though, for me it only happens in v2.
I need to test more to get more accurate results.
In "2.0.27", there is no load on the "CPU" at all. In "2.0.40", even if the setting was "GPU", there was a high load on "CPU" and it was always 100%. With "2.0.45", the load has decreased, but it is still 90-100%.
I guess the load of the cpu may depend on the performance of the CPU. In my case is about 30% but it's still annoying since v1 didn't use any CPU at all. I hope I can do some tests on the next days with the different versions and report a more clear information.
@Kuuko-fokkusugaru tell me the configuration at v1 and v2.
model: onnx or torch f0: dio or harverst or rmvpe or ... chunk: extra: audio devicemode: client or server
@Kuuko-fokkusugaru tell me the configuration at v1 and v2.
model: onnx or torch f0: dio or harverst or rmvpe or ... chunk: extra: audio devicemode: client or server
In my case, v1 never uses the CPU so it works fine. I usually set F0 to rmvpe but I also tried rmvpe_onnx to match v2 configuration. I use a 128 chunk size at max extra. PTH or ONNX files gives the same result. I use client mode.
In v2 I often try with the default settings but I set extra to max. F0 is rmvpe_onnx since there is no rmvpe. Both PTH and ONNX uses the same GPU and CPU. Client mode too.
For testing I use file mode instead of mic because it's easier to just stop the file and monitor performance and resources with no input. Only v2 keeps using about 30% of CPU even without input.
I have an Intel core i7 13700k and a nvidia RTX 3080Ti. I always use GPU mode.
i7-13700k This is the RTX 4070 Ti environment. When using "2.0.47" and setting the settings to "F0Est" fcpe, "Chunk" 7200, and "Extra" 32640, I was able to convert without any "CPU" load. Raising "Extra" increased the load on the "CPU".
It's working much better than before. Thank you very much.
I though FCP was for CPU only. Interesting.
If the "pth" file is Ver. 1 (if an error occurs in "VoiceChangerInfo"), it seems that even "fcpe" is not using the CPU. In the case of Ver2, it seems that the "fcpe" setting uses the CPU to convert audio. In the case of Ver1, it may not be running on "fcpe".
If the "pth" file is Ver. 1 (if an error occurs in "VoiceChangerInfo"), it seems that even "fcpe" is not using the CPU. In the case of Ver2, it seems that the "fcpe" setting uses the CPU to convert audio. In the case of Ver1, it may not be running on "fcpe".
Yes I did some tests today with v1 and it doesn't matter the type of F0 selected. I guess they are all limited by the device selected, CPU or GPU, so they will switch to whichever to match the device.
We've made performance tuning to Client mode. Could you please try version 2.0.50-alpha?
I have monitored the main executable file, the one that eats the most resources, of a couple of different versions, including the old v1. The graphics show the conversion time with idle times in front and back of the conversion of a small 45 seconds audio file to make sure that all the tests are under the same conditions. I ran each test several times to make sure that there were no CPU or GPU usage spikes from first running the conversion. The results are the following:
2.0.50 STD
Chunk 24000, Extra 131040 Sup1 F0: rmvpe_onnx
PTH
Idle Stopped: CPU 00.2% GPU 00.0%
Idle Started: CPU 00.7% GPU 00.0%
Converting: CPU 50.1% GPU 19.2%
ONNX
Idle Stopped: CPU 00.2% GPU 00.0%
Idle Started: CPU 00.7% GPU 00.0%
Converting: CPU 22.1% GPU 14.3%
2.0.50 CUDA
Chunk 24000, Extra 131040 Sup1 F0: rmvpe_onnx
PTH
Idle Stopped: CPU 00.2% GPU 00.0%
Idle Started: CPU 00.7% GPU 00.0%
Converting: CPU 28.3% GPU 20.2%
ONNX
Idle Stopped: CPU 00.2% GPU 00.0%
Idle Started: CPU 00.7% GPU 00.0%
Converting: CPU 28.0% GPU 16.9%
2.0.44
Chunk 24000, Extra 131040 Sup1 F0: rmvpe_onnx
PTH
Idle Stopped: CPU 00.0% GPU 00.0%
Idle Started: CPU 01.4% GPU 00.0%
Converting: CPU 31.3% GPU 20.6%
ONNX
Idle Stopped: CPU 00.0% GPU 00.0%
Idle Started: CPU 02.2% GPU 00.0%
Converting: CPU 30.4% GPU 18.2%
1.5.3.18a
Chunk 24576, Extra 131072 Sup1 F0: rmvpe_onnx
PTH
Idle Stopped: CPU 00.0% GPU 00.0%
Idle Started: CPU 05.4% GPU 18.2%
Converting: CPU 05.9% GPU 20.4%
ONNX
Idle Stopped: CPU 00.0% GPU 00.0%
Idle Started: CPU 04.5% GPU 19.1%
Converting: CPU 04.6% GPU 18.2%
As you can see, the clear winner is still v1 which, while it eats CPU and GPU even when not converting, still uses the least amount of resources while converting. And, while this is still questionable, rmvpe still feels like gives better results than rmvpe_onnx. The tests were using rmvpe_onnx for fair comparison though. 2.0.50 is the one, by far, eating the most resources. This is especially noticeable when using PTH files instead of ONNX.
Please give me a couple of days to test again and update the results of the latest version. SORRY!! 😭😭😭😭
We appreciate your daily cooperation, so please don't worry about it, and if you find out anything new, please share it with us.
I already updated the post quickly. I added the CUDA version and I left the standard version just in case it can be useful. PTH models CPU usage dropped from 50% to 30%. Now both, PTH and ONNX take about the same performance while converting on the CUDA version.
I have a little question that I always wondered. It may not be part of the subject here but, since I am not acknowledged on the matter, why do we use CUDA cores with Nvidia GPUs instead of the TENSOR cores? I thought the TENSOR cores were designed for AI and that they would perform better. But even the standard version uses the GPU even though is not the CUDA version, but GPU usage is the same for ONNX files in both, CUDA and standard. I am really confused about the differences between the CUDA version and the standard, why the GPU usage is the same, and the quality seems the same too, but the CUDA version is a 3GB file vs 600MB file.
I apologize if I misunderstood, but there are some parts that I don't fully understand. I thought that CUDA uses Tensor Cores internally. How can one determine if Tensor Cores are not being used?
It seems there might be one possible cause. Could you please turn off the monitor for me? It's possible that displaying the monitor data on the CUI is putting a load on the system.
from Advanced Setting
I disabled the performance monitor but the CPU usage is the same, about 30%
In my environment, CPU: i9-9900KF GPU:RTX2080
v1 has a higher load than v2.
It's a complete mystery.
V1: CPU usage is around 19-25 https://github.com/user-attachments/assets/f45a0ad6-823e-481f-8f71-081448ba0e96
V2: CPU usage is 9 https://github.com/user-attachments/assets/3470aa1d-158d-4d70-bccd-6813bab04c1f
That's very rare because for me v1 barely have any CPU usage at all lol. I will ask a friend with AMD CPU to test it too. Do you think the model can have any impact? For all the tests I used my main model converted from PTH to ONNX model. I never tested with the default models.
I don't think it's relevant, but I'm not sure. Could you try it with the default model?
Also, just to confirm, are you using something like VBCable that might add some load to the output?
I use VAC (virtual audio cable). VB Cable always gives me issues with some software with stutter and glitched sound. I will try to test with the default models later and see if the result is the same.
Upon reviewing the settings again, I realized I was lacking in knowledge. I checked the CPU load by adjusting the “Extra” and “Chunk” settings in the F0Est “fcpe” scenario.
CPU: i7-13700 GPU: 4070Ti
When lowering the “Chunk” or raising the “Extra,” the CPU load increased. It seems there are better values depending on the CPU and GPU.
When “Extra” is low, the CPU load significantly decreases, but the quality of the conversion seems to drop slightly. At 144000 and above, the conversion quality was very good, but the CPU load was around 20% or more.
For personal streaming, “Chunk” values between 12000 and 19600 seemed appropriate. However, when using Discord or similar for conversations, a value around 7200 provided better response times. However, if “Extra” is set to 65280 or higher during this time, the CPU load reaches 100%.
Therefore, to reduce CPU load, it was necessary to lower both “Chunk” and “Extra.”
As a result:
For personal streaming conversations:
Settings with low CPU load: “Chunk” 14400-19200, “Extra” 32640 or lower (though the conversion quality is not high) Settings with 20-30% CPU load: “Chunk” 14400-19200, “Extra” around 144000 (CPU load does not change above 65280, but conversion quality improves) For conversations on Discord or collaborations:
To improve response times: “Chunk” around 7200, “Extra” 32640 or lower
I hope this helps!
We should still take into account that at max extra of 131000 v1 still uses a barely 5% in comparison with v2 using 30% with the same values. So while the new higher extra values could have a higher impact on the CPU, I don't think it should be near to any of those numbers. I don't see any perceived advantage in v2 vs v1 right now if the performance is worse and the conversion quality is pretty much the same. So I don't see any justification as of right now to sacrifice a 30% of the cpu to get the same results as with the older version.
For now, I still use v1 until v2 is fully fixed and functional. I do look forward for v2 development and improvements but the CPU usage should be a priority to fix right now.
In my environment, CPU: i9-9900KF GPU:RTX2080
v1 has a higher load than v2.
It's a complete mystery.
- V1: CPU usage is around 19-25 https://github.com/user-attachments/assets/f45a0ad6-823e-481f-8f71-081448ba0e96
- V2: CPU usage is 9 https://github.com/user-attachments/assets/3470aa1d-158d-4d70-bccd-6813bab04c1f
I think we need first to figure out this. I could understand that different gpus and cpus can have different behaviors and expected performances. But I don't see a reason for this differences.
For example, I could understand that v1 could have a bit more of cpu usage for you than for me due different generation. But if even for my cpu is barely a 5%, it shouldn't be so big for yours. This is especially important for the v2 case where it uses less cpu for you than for me under the same settings. If your GPU were stronger, 4080, 4090, then I could understand that the GPU is doing a better job and taking some load from the CPU. But in this case a 2080 is not stronger than a 3080Ti since it has less CUDA cores and less Tensor cores (also a different generation).
I need to test @Rakkyotan settings and see if I get similar results. I would like also to know their results using v1 in regards to CPU and GPU usage (please use similar settings to v2 if you test).
I can't think on anything that could lead to more cpu usage in v1 but less in v2. But I guess @w-okada environment may be quite different. My computer only has the common software and a lot of 3D dedicated applications as I am 3D artist. Okada may have a lot of programming software and I guess a lot of dependencies in regards to AI software like python, cuda, etc? I just have the latest nvidia drivers in regards to cuda, I have never installed anything additional about it. I really have no idea but I do love that v1 pretty much don't use any CPU at all. It's a huge difference.
I have compared the CPU load between versions v1 and v2 of “PTH” and summarized the results in a table.
In v1, the CPU load is relatively low if the “Extra” value is 32640 or below, but it increases significantly if the value is 65280 or above.
In v2, the CPU load is high regardless of the value. However, it was curious to note that only the “Extra” values of 7680 and 9600 with “Chunk” set to 7680 did not cause a high load.
As for the GPU, I was unable to monitor it simultaneously, but it appeared to be utilizing between 30% and 50%.
In the case of RVC Client Ver1.5.3.18a, the CPU load remained at only a few percent regardless of the audio or values used.
Wow, that's a very detailed and useful table. Thank you. Is interesting to see a v1 pth model eating 8% CPU at bigger chunk and extra than at minium which is eating 16%. That's double CPU usage at less processing info 🙃. I have never tested with v1 models because all the ones that I use are v2. I didn't know either that would be such a difference between a v1 model vs v2 at all. Maybe because when I started using RVC more seriously, most models were already v2.
Does fcpe sounds better for you than rmvpe_onnx? Or you use it due performance reasons and not about quality?
@Kuuko-fokkusugaru @Rakkyotan We might have finally identified the cause. Could you please try version 2.0.55? I believe we've significantly reduced the CPU load increase.
@Kuuko-fokkusugaru I used fcpe'' without thinking about quality or performance, but out of curiosity to
try using the latest thing.''
However, in the experiment the other day, "rmvpe_onnx
' had a higher CPU usage rate of 1-2%.
I tried "2.0.56".
It was an excellent performance.
Like last time, I changed "Chunk" and "Extra" and summarized the CPU/GPU usage rates in a table.
(Values are estimates.)
If "Extra" is low, the conversion doesn't seem to work.
Also, since both the CPU and GPU have high performance, it is unclear what will happen if the rank is lowered.
However, since the CPU usage rate remained almost unchanged, it seems that if the GPU control is high, the load on the CPU can be significantly reduced.
Thank you very much for the wonderful update.
When thinking about streaming, if "Chunk" is low due to "OBS" or "high load games", it is thought that there will be more scenes where the audio is interrupted. In that case, you may need to raise the "Chunk" considerably.
What's the table below? There are two tables for each type of voice version
The upper table shows the CPU load values (%), and the lower table shows the GPU load values (%).
Oh, my bad. I didn't notice that it says GPU instead of CPU. Sorry 😅
Using the usual settings like the ones I tested above, 2.0.58 gives me very similar results to v1 :D
Around 8-10% of CPU usage and around 16-20% of GPU usage.
@Rakkyotan have you tried the latest 2.0.58 version? Because I can't get the GPU usage anywhere close to what you get. Your GPU usage is very high. Are you running only RVC or also some game? The settings that give me around 16 to 20% of usage give you 89% of usage and that's a huge difference. Even using fcpe or rmvpe_onnx with PTH and ONNX models, both work the same. I know that our GPUs are not the same, but a 4070 may have similar performance to a 3080Ti, maybe even better?? 3080Ti have double the amount of CUDA cores of a 4070 but I thought the Tensor cores were of a newer generation... I am not sure on this but 89% of GPU usage still feels too big. There is a little more of GPU usage when it goes from started iddle to converting. Like, if you stop talking for a while, GPU usage drops to 0, then once you start talking it jumps a bit to around 30% tne stabilizes down to 16-20% but never 89%.
I didn't test the prior version because, when I wanted to try, 2.0.58 was already out so I tested the newer one right away.
@w-okada thank you so much for the hard work, you really have improved the software 😄 . There is still more to test but it surely works way better than before. CPU usage still higher than v1 for me, but 10% is still better than 30% 😋
Regarding the measurement conditions, only RVC is running. Regarding "GPU", we have visually measured the "maximum value (value close to it)", so as "kuuko" said, the value will jump at first, but then it will stabilize, and it will be 0% when not converting audio. Masu. If it's a "stable value when you keep speaking", it will be slightly lower than the value in the previous table. I found that if I raised "Chunk", "GPU usage" decreased, but I don't know if this value is large or small because I only have one graphics board.
Thank you for updating RVC. We had a great delivery today as well.
I forgot to mention it, but the "output buffer size ratio" in "Advanced Setting" is set to "15". There may also be differences depending on the "CPU" and "GPU" loads.
Does v1 also had such big GPU usage? By v1 I mean RVC v1.5.3.18a
I have never measured it. However, I feel that the GPU fan never moved. I will measure it if necessary.
Voice Changer Version
vcclient_win_cuda_2.0.45-alpha.zip
Operational System
Windows 11
GPU
NVIDIA Geforce RTX 4070 Ti
CUDA Version
12.5
Read carefully and check the options
Does pre-installed model work?
No
Model Type
MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.18a.zip
Issue Description
CPU i7-13700 Chunk 7200 EXtra 65280 F0Set fcpe OUTPUT buffer 7
I am always grateful for your help.
Until 2.0.27, when converting audio. The usage rate of the "CPU" did not increase, and audio conversion was performed only by processing within the "GPU". However, from 2.0.40, when converting audio, not only "NVIDIA" but also "CPU" operates, and the "CPU" usage rate becomes 100%. (Both "pth" and "onnx") Have the specifications changed like this? Thank you.
Application Screenshot
No response
Logs on console
2024-07-26 16:21:26,146 - vcclient - gpu_device_manager - INFO - Reloading GPU info - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 120 2024-07-26 16:21:26,388 - vcclient - gpu_device_manager - ERROR - Failed to reload_gpu_info_for_win. Failed to resolve Python.Runtime.Loader.Initialize from C:\RVC2045_internal\pythonnet\runtime\Python.Runtime.dll. If you are using torch_cuda, this error can be ignored. - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 50 2024-07-26 16:21:26,388 - vcclient - gpu_device_manager - INFO - GPU[sys]:[GPUInfo(name='cpu', device_id='-1', adapter_ram=0, device_id_int=-1, cuda_compute_version_major=-1, cuda_compute_version_minor=-1)] - vcclient_dev\voice_changer\gpu_device_manager\gpu_device_manager.py - 123