Google Colab is still broken:

[PhoenixStormJr]

! python3 test/test.py

Initializing VoiceFixer... /usr/local/lib/python3.11/dist-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. WeightNorm.apply(module, name, dim) Traceback (most recent call last): File "/content/voicefixer/test/test.py", line 41, in voicefixer = VoiceFixer() ^^^^^^^^^^^^ File "/usr/local/lib/python3.11/dist-packages/voicefixer/base.py", line 12, in init self._model = voicefixer_fe(channels=2, sample_rate=44100) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/dist-packages/voicefixer/restorer/model.py", line 152, in init self.f_helper = FDomainHelper( ^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/dist-packages/voicefixer/tools/modules/fDomainHelper.py", line 22, in init self.stft = STFT(n_fft=window_size, hop_length=hop_size, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/dist-packages/torchlibrosa/stft.py", line 177, in init fft_window = librosa.util.pad_center(fft_window, n_fft) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: pad_center() takes 1 positional argument but 2 were given /content

! pip install --upgrade ddsp

error: resolution-too-deep

× Dependency resolution exceeded maximum depth ╰─> Pip cannot resolve the current dependencies as the dependency graph is too complex for pip to solve efficiently.

hint: Try adding lower bounds to constrain your dependencies, for example: 'package>=2.0.0' instead of just 'package'.