[ISSUE for v2]: bad static/glitchy

[akirawashere]

Voice Changer Version

vcclient_win_cuda_2.0.65-beta

Operational System

Windows 11

GPU

3080

CUDA Version

2.0.65-beta

Read carefully and check the options

• If you use win_cuda_torch_cuda edition, setup cuda? see here
• If you use win_cuda edition, setup cuda and cudnn? see here
• If you use mac edition, client is not launched automatically. Use chrome to open application.?
• I've tried to change the Chunk Size
• I've tried to set the Index to zero
• I've read the tutorial
• I've tried to extract to another folder (or re-extract) the .zip file

Does pre-installed model work?

No

Model Type

RVC

Issue Description

bad static/glitch

Application Screenshot

No response

Logs on console

2024-11-02 22:10:40,163 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51766 - "GET /api/voice-changer-manager/information HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,164 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51769 - "GET /assets/gui_settings/version.txt HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,165 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51768 - "GET /assets/gui_settings/GUI.json HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,166 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51765 - "GET /api/configuration-manager/configuration HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,176 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51767 - "GET /api/audio-device-manager/input_devices HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,178 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51765 - "GET /favicon.ico HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,179 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51760 - "GET /api/audio-device-manager/output_devices HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,180 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51766 - "GET /api/gpu-device-manager/devices HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,187 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51769 - "GET /api/module-manager/modules HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,192 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51768 - "GET /api/sample-manager/samples HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,347 - vcclient - voice_changer_manage - INFO - Getting voice changer manager information. - vcclient_dev\voice_changer\voice_change_manager\voice_changer_manager.py - 22
2024-11-02 22:10:40,348 - vcclient - vcserver_rest_api_vo - INFO - get_voice_changer_information local_voice_changer_interface_active=False voice_changer_information=VoiceChangerInformation(slot_index=7, pitch_estimator_type='crepe_full', 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=48000, resample_ratio_in=0.3333333333333333, resample_ratio_out=1.0, resample_ratio_monitor=1.0, 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=1.0, pipeline_info=RVCPipelineInfo(slot_index=7, input_sample_rate=16000, output_sample_rate=48000, chunk_sec=1.0, slot_info={'slot_index': 7, 'voice_changer_type': 'RVC', 'name': 'egirl', 'description': '', 'credit': '', 'terms_of_use_url': '', 'icon_file': None, 'speakers': {}, 'model_file': WindowsPath('egirl.pth'), 'index_file': WindowsPath('added_IVF2182_Flat_nprobe_1_egirl.index'), 'is_onnx': False, 'inferencer_type': 'pyTorchRVCv2', 'sample_rate': 48000, 'is_f0': True, 'deprecated': False, 'embedder': 'hubert_base_l12', 'pitch_estimator': 'rmvpe_onnx', 'sample_id': None, 'version': 'v2', 'chunk_sec': 0.5, 'pitch_shift': 0, '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='rmvpe_onnx', model_file=WindowsPath('modules/rmvpe/rmvpe_20231006.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': {}}"), inferencer_info=RVCInferencerInfo(inferencer_type='pyTorchRVCv2', model_file=WindowsPath('model_dir/7/egirl.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 - 124
2024-11-02 22:10:40,362 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51767 - "GET /api/slot-manager/slots HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,409 - vcclient - rvc_pipeline - INFO - noise gate -113.4910522594103 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:40,452 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51760 - "GET /api/configuration-manager/configuration HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,454 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51765 - "GET /api/voice-changer-manager/information HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:40,456 - uvicorn.ac - h11_impl - INFO - 127.0.0.1:51767 - "GET /api/configuration-manager/configuration HTTP/1.1" 200 - uvicorn\protocols\http\h11_impl.py - 477
2024-11-02 22:10:41,331 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:42,330 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:43,338 - vcclient - rvc_pipeline - INFO - noise gate -110.0533923228704 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:44,332 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:45,333 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:46,331 - vcclient - rvc_pipeline - INFO - noise gate -113.2629594850645 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:47,332 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:48,330 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:49,331 - vcclient - rvc_pipeline - INFO - noise gate -113.97632962064955 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:50,330 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:51,338 - vcclient - rvc_pipeline - INFO - noise gate -119.37492101658337 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:52,331 - vcclient - rvc_pipeline - INFO - noise gate -102.13287552145854 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:53,336 - vcclient - rvc_pipeline - INFO - noise gate -119.454867302483 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:54,332 - vcclient - rvc_pipeline - INFO - noise gate -inf < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222
2024-11-02 22:10:55,332 - vcclient - rvc_pipeline - INFO - noise gate -116.01828217999142 < -85.0 - vcclient_dev\voice_changer\voice_change_manager\vc_pipelines\rvc_pipeline.py - 222

[Kuuko-fokkusugaru]

Application screenshot is missing. Also model info.
Does it happens with included models?
Could you share an example clip of how it sounds and a screenshot of the software WHILE it sounds "bad"? It's important for the screenshot to be taken while the software is running and converting voice to see the details of the conversion. Once I can listen how it sounds and see your configuration on a screenshot, I will be able to further help you.

[akirawashere]

hmm i think it happens when im streaming, idk I have a 3080

[Kuuko-fokkusugaru]

There is no example clip neither the screenshot was taken while using the software (speaking) like requested. I can't do anything with the info given but seeing that you are using vb cable, uninstall it and install virtual audio cable lite instead which is free and there is no glitchy sound unlike vb cable.

[akirawashere]

hmm what would the difference be between the 2?

[Kuuko-fokkusugaru]

Vb cable has issues while virtual audio cable lite doesn't.