[ISSUE]: GPU not utilized for uploaded models

Voice Changer Version

MMVCServerSIO_win_onnxdirectML-cuda_v.1.5.3.18a

Operational System

Windows 10

GPU

RX 5700XT

Read carefully and check the options

[X] I've tried to Clear Settings
[X] Sample/Default Models are working
[X] I've tried to change the Chunk Size
[X] GUI was successfully launched
[X] I've read the tutorial
[X] I've tried to extract to another folder (or re-extract) the .zip file

Model Type

RVC

Issue Description

All included RVC and Beatrice models run very well. They're clear with no skipping and only a ~500ms delay.

However, every model that I have downloaded and uploaded all run very poorly. There's a long delay, and the voice is inconsistent and choppy. When checking task manager while using a default included model, I can see that the GPU usage is between 10-20%, sometimes a little more. But when I try using an uploaded model, the GPU usage never goes above 2 or 3%, all work is being done by my CPU.

I noticed that the included models only list the model, they seemingly don't have an index, so I tried uploading a model without an index and the issue was the same.

Application Screenshot

Screenshot 2024-06-16 211601

Logs on console

C:\Users\user\Downloads\MMVCServerSIO>MMVCServerSIO.exe -p 18888 --https false --content_vec_500 pretrain/checkpoint_best_legacy_500.pt --content_vec_500_onnx pretrain/content_vec_500.onnx --content_vec_500_onnx_on true --hubert_base pretrain/hubert_base.pt --hubert_base_jp pretrain/rinna_hubert_base_jp.pt --hubert_soft pretrain/hubert/hubert-soft-0d54a1f4.pt --nsf_hifigan pretrain/nsf_hifigan/model --crepe_onnx_full pretrain/crepe_onnx_full.onnx --crepe_onnx_tiny pretrain/crepe_onnx_tiny.onnx --rmvpe pretrain/rmvpe.pt --model_dir model_dir --samples samples.json Booting PHASE :main PYTHON:3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Activating the Voice Changer. [Voice Changer] download sample catalog. samples_0004_t.json [Voice Changer] download sample catalog. samples_0004_o.json [Voice Changer] download sample catalog. samples_0004_d.json [Voice Changer] model_dir is already exists. skip download samples. Internal_Port:18888 protocol: HTTP

Please open the following URL in your browser.
http://<IP>:<PORT>/
In many cases, it will launch when you access any of the following URLs.
http://127.0.0.1:18888/

[VCClient] Access http://127.0.0.1:18888/ [VCClient] wait web server...0 http://127.0.0.1:18888/ Booting PHASE :main Booting PHASE :MMVCServerSIO [Voice Changer] VoiceChangerManager initializing... [Voice Changer] model slot is changed -1 -> 6 ................RVC [Voice Changer] [RVCr2] Creating instance VoiceChangerV2 Initialized (GPU_NUM(cuda):0, mps_enabled:False, onnx_device:CPU-DML) [Voice Changer][RVC]: update_settings gpu:0 [Voice Changer][RVCr2] Initializing... gin_channels: 256 self.spk_embed_dim: 109 [Voice Changer] generate new embedder. (no embedder) [Voice Changer] Loading index... Try loading... model_dir\6\added_IVF389_Flat_nprobe_1.index GENERATE INFERENCER<voice_changer.RVC.inferencer.RVCInferencer.RVCInferencer object at 0x000001A6F2E03F70> GENERATE EMBEDDER<voice_changer.RVC.embedder.OnnxContentvec.OnnxContentvec object at 0x000001A72B7F0610> GENERATE PITCH EXTRACTOR<voice_changer.RVC.pitchExtractor.RMVPEOnnxPitchExtractor.RMVPEOnnxPitchExtractor object at 0x000001A72B7F0640> [Voice Changer] [RVC] Initializing... done [Voice Changer][RVC]: update_settings f0Detector:rmvpe_onnx [Voice Changer][RVC]: update_settings serverReadChunkSize:192 [Voice Changer][RVC]: update_settings enableServerAudio:0 [Voice Changer][RVC]: update_settings extraConvertSize:8192 [Voice Changer][RVC]: update_settings modelSlotIndex:1718583141006 [Voice Changer] VoiceChangerManager initializing... done. [Voice Changer] MMVC_Rest initializing... [Voice Changer] MMVC_Rest initializing... done. [Voice Changer] MMVC_SocketIOApp initializing... [Voice Changer] MMVC_SocketIOApp initializing... done. [VCClient] wait web server... done 200 [2024-06-16 21:14:13] connet sid : PJL8cGZVTqtQ0WGxAAAC [2024-06-16 21:14:13] connet sid : ft3bCp0FgtLXTgGJAAAD [Voice Changer] update configuration: modelSlotIndex 1718586880000Beatrice-JVS [Voice Changer] model slot is changed 6 -> Beatrice-JVS ................Beatrice [Voice Changer] [Beatrice] Creating instance VoiceChangerV2 Initialized (GPU_NUM(cuda):0, mps_enabled:False, onnx_device:CPU-DML) Pipeline has been deleted [Voice Changer] [Beatrice] Initializing... [Voice Changer] [Beatrice] Initializing... done [Voice Changer][Beatrice]: update_settings gpu:0 [Voice Changer][Beatrice]: update_settings f0Detector:rmvpe_onnx [Voice Changer][Beatrice]: update_settings serverReadChunkSize:192 [Voice Changer][Beatrice]: update_settings enableServerAudio:0 [Voice Changer][Beatrice]: update_settings extraConvertSize:8192 [Voice Changer][Beatrice]: update_settings modelSlotIndex:1718586880000Beatrice-JVS

w-okada / voice-changer