frequent error occur - Githubissues

HikariNasa commented 1 year ago

Issue Type

Others

vc client version number

1.5.3.6

OS

windows 10

GPU

gt 710 2 gb

Clear setting

yes

Sample model

yes

Input chunk num

yes

Voice Changer type

RVC

Model type

onnx

Situation

Traceback (most recent call last): File "voice_changer\VoiceChanger.py", line 217, in on_request_sola File "voice_changer\RVC\RVC.py", line 131, in generate_input RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

w-okada commented 1 year ago

more info

w-okada commented 1 year ago

no res close

ghost commented 1 year ago

Yep, i have the same error

no res close

What i can provide you for solve this? I have the same error Traceback (most recent call last): File "voice_changer\VoiceChanger.py", line 228, in on_request_sola File "voice_changer\RVC\RVC.py", line 163, in inference File "torchaudio\functional\functional.py", line 1604, in resample File "torchaudio\functional\functional.py", line 1502, in _get_sinc_resample_kernel RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

ghost commented 1 year ago

Full logs here

C:\Users\z\Downloads\MMVCServerSIO_win_onnxgpu-cuda_v.1.5.3.8\MMVCServerSIO>MMVCServerSIO.exe -p 18888 --https false --content_vec_500 pretrain/checkpoint_best_legacy_500.pt --content_vec_500_onnx pretrain/checkpoint_best_legacy_500.onnx --content_vec_500_onnx_on false --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 --model_dir model_dir --samples samples.json CUDA_LAUNCH_BLOCKING=1 Booting PHASE :main Voice Changerを起動しています。 ++[Voice Changer] model_dir is already exists. skip download samples. Internal_Port:18888 protocol: HTTP

ブラウザで次のURLを開いてください.
http://<IP>:<PORT>/
多くの場合は次のいずれかのURLにアクセスすると起動します。
http://localhost:18888/

Preparing your application. Please wait... (node:5752) electron: Failed to load URL: http://localhost:18888/ with error: ERR_CONNECTION_REFUSED (Use voice-changer-native-client --trace-warnings ... to show where the warning was created) Booting PHASE :main Booting PHASE :MMVCServerSIO torch\cuda__init__.py:152: UserWarning: Found GPU0 NVIDIA GeForce GT 710 which is of cuda capability 3.5. PyTorch no longer supports this GPU because it is too old. The minimum cuda capability supported by this library is 3.7.

warnings.warn(old_gpu_warn % (d, name, major, minor, min_arch // 10, min_arch % 10)) [Voice Changer] model slot is changed -1 -> 4 ................RVC 2023-07-04 23:51:25 | INFO | faiss.loader | Loading faiss with AVX2 support. 2023-07-04 23:51:25 | INFO | faiss.loader | Could not load library with AVX2 support due to: ModuleNotFoundError("No module named 'faiss.swigfaiss_avx2'") 2023-07-04 23:51:25 | INFO | faiss.loader | Loading faiss. 2023-07-04 23:51:25 | INFO | faiss.loader | Successfully loaded faiss. [Voice Changer] [RVC] Creating instance [Voice Changer] [RVC] Initializing... inferencerTypeinferencerTypeinferencerTypeinferencerType pyTorchRVCv2 gin_channels: 256 self.spk_embed_dim: 109 [Voice Changer] generate new embedder. (no embedder) Preparing your application. Please wait... (node:5752) electron: Failed to load URL: http://localhost:18888/ with error: ERR_CONNECTION_REFUSED [Voice Changer] Loading index... Try loading... model_dir\4\added_IVF1035_Flat_nprobe_1_Rakkun_v2.index GENERATE INFERENCER <voice_changer.RVC.inferencer.RVCInferencerv2.RVCInferencerv2 object at 0x00000286F9F05FC0> GENERATE EMBEDDER <voice_changer.RVC.embedder.FairseqHubert.FairseqHubert object at 0x000002869F75A470> GENERATE PITCH EXTRACTOR <voice_changer.RVC.pitchExtractor.HarvestPitchExtractor.HarvestPitchExtractor object at 0x000002869F75A4D0> [Voice Changer] [RVC] Initializing... done VoiceChanger Initialized (GPU_NUM:1, mps_enabled:False) [Voice Changer][RVC]: update_settings gpu 0 [Voice Changer] [RVC] Initializing... inferencerTypeinferencerTypeinferencerTypeinferencerType pyTorchRVCv2 gin_channels: 256 self.spk_embed_dim: 109 [Voice Changer] embeder type is not match EnumEmbedderTypes.hubert hubert_base [Voice Changer] generate new embedder. (not match) Preparing your application. Please wait... (node:5752) electron: Failed to load URL: http://localhost:18888/ with error: ERR_CONNECTION_REFUSED [Voice Changer] Loading index... Try loading... model_dir\4\added_IVF1035_Flat_nprobe_1_Rakkun_v2.index GENERATE INFERENCER <voice_changer.RVC.inferencer.RVCInferencerv2.RVCInferencerv2 object at 0x00000286F9F05CF0> GENERATE EMBEDDER <voice_changer.RVC.embedder.FairseqHubert.FairseqHubert object at 0x00000286A7259DE0> GENERATE PITCH EXTRACTOR <voice_changer.RVC.pitchExtractor.HarvestPitchExtractor.HarvestPitchExtractor object at 0x00000286A7259E40> [Voice Changer] [RVC] Initializing... done [Voice Changer][RVC]: update_settings enableServerAudio 0 [Voice Changer][RVC]: update_settings modelSlotIndex 1688539442004 [Voice Changer][RVC]: update_settings enableServerAudio 0 [2023-07-04 23:51:37] connet sid : aeBZ1uQstDx9-K-QAAAB [2023-07-04 23:51:37] connet sid : 7jI3d9ErkADH4Z17AAAD Generated Strengths: for prev:(4096,), for cur:(4096,) [Voice Changer] VC PROCESSING EXCEPTION!!! CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Traceback (most recent call last): File "voice_changer\VoiceChanger.py", line 228, in on_request_sola File "voice_changer\RVC\RVC.py", line 163, in inference File "torchaudio\functional\functional.py", line 1604, in resample File "torchaudio\functional\functional.py", line 1502, in _get_sinc_resample_kernel RuntimeError: CUDA error: no kernel image is available for execution on the device CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

ghost commented 1 year ago

I think the problem is in.

Preparing your application. Please wait... (node:5752) electron: Failed to load URL: http://localhost:18888/ with error: ERR_CONNECTION_REFUSED (Use voice-changer-native-client --trace-warnings ... to show where the warning was created) Booting PHASE :main Booting PHASE :MMVCServerSIO torch\cudainit.py:152: UserWarning: Found GPU0 NVIDIA GeForce GT 710 which is of cuda capability 3.5. PyTorch no longer supports this GPU because it is too old. The minimum cuda capability supported by this library is 3.7.

Maybe this can help https://stackoverflow.com/questions/33651810/the-minimum-required-cuda-capability-is-3-5 In the responce 3 is mentioned this: