search

CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
52.75k stars 8.81k forks source link

error demo_cli.py #160

Closed Stellarize closed 4 years ago

Stellarize commented 5 years ago

when runninf python demo_cli.py get this error :

Testing your configuration with small inputs. Testing the encoder... Traceback (most recent call last): File "demo_cli.py", line 76, in <module> encoder.embed_utterance(np.zeros(encoder.sampling_rate)) File "/home/kubutsushimuzan/Bureau/Real-Time-Voice-Cloning/encoder/inference.py", line 145, in embed_utterance frames = audio.wav_to_mel_spectrogram(wav) File "/home/kubutsushimuzan/Bureau/Real-Time-Voice-Cloning/encoder/audio.py", line 53, in wav_to_mel_spectrogram n_mels=mel_n_channels File "/home/kubutsushimuzan/.local/lib/python3.7/site-packages/librosa/feature/spectral.py", line 1391, in melspectrogram mel_basis = filters.mel(sr, n_fft, **kwargs) File "/home/kubutsushimuzan/.local/lib/python3.7/site-packages/librosa/filters.py", line 247, in mel lower = -ramps[i] / fdiff[i] ValueError: operands could not be broadcast together with shapes (1,201) (0,)

raanubis commented 5 years ago

did you installed all dependencies?

pip install requirements.txt ?

Stellarize commented 5 years ago

yes i installed all the dependencies

raanubis commented 5 years ago

librosa version? if librosa <= 0.6.2 than update the same with numpy minimum numpy version 1.14.3

Stellarize commented 5 years ago

ok i'll try and make a feedback

ghost commented 4 years ago

Hi there @Stellarize . Would you kindly pull the latest version of the repo and try again? We have updated the codebase quite a bit in the last few weeks and are unable to troubleshoot errors on an old version of the toolbox.

ghost commented 4 years ago

Feel free the reopen this issue if you experience problems with the latest code.