search

CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
51.54k stars 8.64k forks source link

error after runnig demo toolbox #1222

Open gerdaa opened 1 year ago

gerdaa commented 1 year ago

Hello,

When I run demo_toolbox.py I get this error. How can I fix this errors?

===================================================== (voice-clone) C:\Users\Linda\Desktop\voice>python demo_cli.py Arguments: enc_model_fpath: saved_models\default\encoder.pt syn_model_fpath: saved_models\default\synthesizer.pt voc_model_fpath: saved_models\default\vocoder.pt cpu: False no_sound: False seed: None

Running a test of your configuration...

Using CPU for inference.

Preparing the encoder, the synthesizer and the vocoder... Loaded encoder "encoder.pt" trained to step 1564501 Synthesizer using device: cpu Building Wave-RNN Trainable Parameters: 4.481M Loading model weights at saved_models\default\vocoder.pt Testing your configuration with small inputs. Testing the encoder... Traceback (most recent call last): File "C:\Users\Linda\Desktop\voice\demo_cli.py", line 80, in encoder.embed_utterance(np.zeros(encoder.sampling_rate)) File "C:\Users\Linda\Desktop\voice\encoder\inference.py", line 144, in embed_utterance frames = audio.wav_to_mel_spectrogram(wav) File "C:\Users\Linda\Desktop\voice\encoder\audio.py", line 58, in wav_to_mel_spectrogram frames = librosa.feature.melspectrogram( TypeError: melspectrogram() takes 0 positional arguments but 2 positional arguments (and 2 keyword-only arguments) were given

Thanks already, Gerdaa

radhavishnu commented 1 year ago

Install the version of librosa they used, or go to each loaction and give parameters y=, n_mels= example librosa.stft(y=y, n_fft=hparams.n_fft, hop_length=get_hop_size(hparams), win_length=hparams.win_size)