search

Anjok07 / ultimatevocalremovergui

GUI for a Vocal Remover that uses Deep Neural Networks.
MIT License
18.16k stars 1.36k forks source link

What is the minimux CUDA Version Support? #1251

Open uhuame opened 7 months ago

uhuame commented 7 months ago

My GPU is GeForce GTX 760 and the highest CUDA support version is 11.4 the readme fille metion the lowest GPU should be RTX 1060, but I don't know what it is, I had search from internet but nothing When i run with GPU Conversion(in any METHOD).it report that. Seems is because my GPU not support.

`Last Error Received:

Process: Ensemble Mode

If this error persists, please contact the developers with the error details.

Raw Error Details:

RuntimeError: "cuFFT error: CUFFT_INVALID_DEVICE" Traceback Error: " File "/home/fkt/Projects/ultimatevocalremovergui-master/UVR.py", line 4716, in process_start seperator.seperate() File "/home/fkt/Projects/ultimatevocalremovergui-master/separate.py", line 287, in seperate source = self.demix_base(mix, is_ckpt=self.is_mdx_ckpt)[0] File "/home/fkt/Projects/ultimatevocalremovergui-master/separate.py", line 366, in demix_base tar_waves = self.run_model(mix_wave, is_ckpt=is_ckpt, is_match_mix=is_match_mix) File "/home/fkt/Projects/ultimatevocalremovergui-master/separate.py", line 380, in run_model spek = self.stft(mix.to(self.device))*self.adjust File "/home/fkt/Projects/ultimatevocalremovergui-master/separate.py", line 395, in stft x = torch.stft(x, n_fft=self.n_fft, hop_length=self.hop, window=self.window, center=True,return_complex=True) File "/home/fkt/Projects/ultimatevocalremovergui-master/lib64/python3.9/site-packages/torch/functional.py", line 632, in stft return _VF.stft(input, n_fft, hop_length, win_length, window, # type: ignore[attr-defined] "

Error Time Stamp [2024-03-24 22:25:15]

Full Application Settings:

vr_model: UVR-DeNoise aggression_setting: 10 window_size: 320 batch_size: Default crop_size: 256 is_tta: False is_output_image: False is_post_process: False is_high_end_process: False post_process_threshold: 0.2 vr_voc_inst_secondary_model: No Model Selected vr_other_secondary_model: No Model Selected vr_bass_secondary_model: No Model Selected vr_drums_secondary_model: No Model Selected vr_is_secondary_model_activate: False vr_voc_inst_secondary_model_scale: 0.9 vr_other_secondary_model_scale: 0.7 vr_bass_secondary_model_scale: 0.5 vr_drums_secondary_model_scale: 0.5 demucs_model: v3 | UVR_Model_1 segment: Default overlap: 0.25 shifts: 2 chunks_demucs: Auto margin_demucs: 44100 is_chunk_demucs: False is_chunk_mdxnet: False is_primary_stem_only_Demucs: False is_secondary_stem_only_Demucs: False is_split_mode: True is_demucs_combine_stems: True demucs_voc_inst_secondary_model: No Model Selected demucs_other_secondary_model: No Model Selected demucs_bass_secondary_model: No Model Selected demucs_drums_secondary_model: No Model Selected demucs_is_secondary_model_activate: False demucs_voc_inst_secondary_model_scale: 0.9 demucs_other_secondary_model_scale: 0.7 demucs_bass_secondary_model_scale: 0.5 demucs_drums_secondary_model_scale: 0.5 demucs_pre_proc_model: No Model Selected is_demucs_pre_proc_model_activate: False is_demucs_pre_proc_model_inst_mix: False mdx_net_model: Choose Model chunks: Auto margin: 44100 compensate: Auto is_denoise: False is_invert_spec: False is_mixer_mode: False mdx_batch_size: Default mdx_voc_inst_secondary_model: No Model Selected mdx_other_secondary_model: No Model Selected mdx_bass_secondary_model: No Model Selected mdx_drums_secondary_model: No Model Selected mdx_is_secondary_model_activate: False mdx_voc_inst_secondary_model_scale: 0.9 mdx_other_secondary_model_scale: 0.7 mdx_bass_secondary_model_scale: 0.5 mdx_drums_secondary_model_scale: 0.5 is_save_all_outputs_ensemble: True is_append_ensemble_name: False chosen_audio_tool: Manual Ensemble choose_algorithm: Min Spec time_stretch_rate: 2.0 pitch_rate: 2.0 is_gpu_conversion: True is_primary_stem_only: False is_secondary_stem_only: False is_testing_audio: False is_add_model_name: False is_accept_any_input: False is_task_complete: False is_normalization: False is_create_model_folder: False mp3_bit_set: 320k save_format: WAV wav_type_set: PCM_16 help_hints_var: False model_sample_mode: False model_sample_mode_duration: 30 demucs_stems: All Stems`

ChrisTG742 commented 7 months ago

Hi, from my own experiments I can confirm that the 760 is not supported and never will since the CUDA-support is too low. The 1060 is probably the smallest card that works, but I doubt that it has enough resources so that you would gain a real speed increase compared to CPU processing.