search

nomadkaraoke / python-audio-separator

Easy to use stem (e.g. instrumental/vocals) separation from CLI or as a python package, using a variety of amazing pre-trained models (primarily from UVR)
MIT License
477 stars 82 forks source link

ValueError: Unsupported Model File: parameters for MD5 hash dac7f142d5adf52ee84c1e900a3c2725 could not be found in UVR model data file for MDX or VR arc #85

Closed Lixi20 closed 3 months ago

Lixi20 commented 3 months ago

(myenv) PS D:\AIDownloads\DS测试工具\音轨分离> audio-separator D:\AIDownloads\DS测试工具\测试音频\玫瑰的故事E02_1.mp3 --output_format=mp3 --single_stem=Vocals --sample_rate=44100 --demucs_shifts=4 --demucs_overlap=0.25 --model_filename 955717e8-8726e21a.th --output_dir D:\AIDownloads\DS测试工具\测试音频\out 2024-07-12 10:55:19.793 - INFO - cli - Separator version 0.17.5 beginning with input file: D:\AIDownloads\DS测试工具\测试音频\玫瑰的故事E02_1.mp3 2024-07-12 10:55:19.794 - INFO - separator - Separator version 0.17.5 instantiating with output_dir: D:\AIDownloads\DS测试工具\测试音频\out, output_format: mp3 2024-07-12 10:55:19.794 - INFO - separator - Operating System: Windows 10.0.22631 2024-07-12 10:55:19.794 - INFO - separator - System: Windows Node: Geek Release: 10 Machine: AMD64 Proc: AMD64 Family 25 Model 97 Stepping 2, AuthenticAMD 2024-07-12 10:55:19.794 - INFO - separator - Python Version: 3.10.6 2024-07-12 10:55:19.794 - INFO - separator - PyTorch Version: 2.3.1+cpu 2024-07-12 10:55:19.808 - INFO - separator - FFmpeg installed: ffmpeg version 6.0-full_build-www.gyan.dev Copyright (c) 2000-2023 the FFmpeg developers 2024-07-12 10:55:19.809 - INFO - separator - ONNX Runtime GPU package installed with version: 1.18.1 2024-07-12 10:55:19.809 - INFO - separator - No hardware acceleration could be configured, running in CPU mode 2024-07-12 10:55:19.809 - INFO - separator - Loading model 955717e8-8726e21a.th... 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 84.1M/84.1M [05:21<00:00, 262kiB/s] 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 21.0/21.0 [00:00<?, ?iB/s] Traceback (most recent call last): File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "D:\AIDownloads\DS测试工具\音轨分离\myenv\Scripts\audio-separator.exe__main__.py", line 7, in File "D:\AIDownloads\DS测试工具\音轨分离\myenv\lib\site-packages\audio_separator\utils\cli.py", line 175, in main separator.load_model(model_filename=args.model_filename) File "D:\AIDownloads\DS测试工具\音轨分离\myenv\lib\site-packages\audio_separator\separator\separator.py", line 641, in load_model model_data = self.load_model_data_using_hash(model_path) File "D:\AIDownloads\DS测试工具\音轨分离\myenv\lib\site-packages\audio_separator\separator\separator.py", line 615, in load_model_data_using_hash raise ValueError(f"Unsupported Model File: parameters for MD5 hash {model_hash} could not be found in UVR model data file for MDX or VR arch.") ValueError: Unsupported Model File: parameters for MD5 hash dac7f142d5adf52ee84c1e900a3c2725 could not be found in UVR model data file for MDX or VR arc

Lixi20 commented 3 months ago

audio-separator 0.17.5

beveradb commented 3 months ago

Ah, sorry this isn't super clear with the demucs models but you need to specify the model file name rather than one of the partial filenames

So, instead of --model_filename 955717e8-8726e21a.th you would use --model_filename htdemucs.yaml

Hope that helps!