Open imjakedeason opened 6 months ago
downgrade the samplerate module
pip install samplerate==0.1.0
downgrade the samplerate module
pip install samplerate==0.1.0
thank you, it worked
downgrade the samplerate module
pip install samplerate==0.1.0
i got this error massage, plz help,thanks soooo much!
stft of wave source... done
100% 83/83 [00:41<00:00, 2.01it/s]
100% 84/84 [00:43<00:00, 1.94it/s]
Traceback (most recent call last):
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 307, in <module>
main()
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 302, in main
process.inference()
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/main.py", line 122, in inference
y_wave = spec_utils.cmb_spectrogram_to_wave(y_spec_m, mp, input_high_end_h, input_high_end_)
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/lib/spec_utils.py", line 340, in cmb_spectrogram_to_wave
wave = librosa.resample(spectrogram_to_wave(spec_s, bp['hl'], mp, False), bp['sr'], sr, res_type="sinc_fastest")
File "/content/drive/MyDrive/VocalRemover5-COLAB_arch/lib/spec_utils.py", line 297, in spectrogram_to_wave
wave_left = librosa.istft(spec_left, hop_length=hop_length)
File "/usr/local/lib/python3.10/dist-packages/librosa/util/decorators.py", line 88, in inner_f
return f(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/librosa/core/spectrum.py", line 394, in istft
dtype = util.dtype_c2r(stft_matrix.dtype)
File "/usr/local/lib/python3.10/dist-packages/librosa/util/decorators.py", line 88, in inner_f
return f(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/librosa/util/utils.py", line 2185, in dtype_c2r
np.dtype(complex): np.dtype(np.float).type,
File "/usr/local/lib/python3.10/dist-packages/numpy/__init__.py", line 319, in __getattr__
raise AttributeError(__former_attrs__[attr])
AttributeError: module 'numpy' has no attribute 'float'.
`np.float` was a deprecated alias for the builtin `float`. To avoid this error in existing code, use `float` by itself.
Doing this will not modify any behavior and is safe. If you specifically wanted the numpy scalar type, use `np.float64` here.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations. Did you mean: 'cfloat'?
Notebook took: 112.1s
You probably want to specify all libsora's functions parameters in lib/spec_utils.py
For example, the line 15, after clarifying which parameter the value belongs to:
inp, sr=mp.param['band'][bands_n+1]['sr'], mono=False, dtype=np.float32, res_type=mp.param['band'][bands_n+1]['res_type'])
你可能想在 lib/spec_utils.py 中指定所有 libsora 的函数参数, 例如第 15 行,在明确该值属于哪个参数后:
inp, sr=mp.param['band'][bands_n+1]['sr'], mono=False, dtype=np.float32, res_type=mp.param['band'][bands_n+1]['res_type'])
Sorry, I'm a novice and I just started using this program. I don't quite understand what you mean by line 15. I didn't see your example in the error massage either. Does that mean I have to change the source code?
yes
Sorry to bother you again. I can't understand the code of this project. I just want to use this tool to separate the audio. Can you tell me how to change the code in detail? It doesn't matter if you don't want to. Thank you very much!!!
Everything worked for me for months and I haven't changed anything, and now I'm getting an error: