BenAAndrew / Voice-Cloning-App

A Python/Pytorch app for easily synthesising human voices
BSD 3-Clause "New" or "Revised" License
1.4k stars 233 forks source link

Error before training #177

Open Autachi opened 1 year ago

Autachi commented 1 year ago

When I try to train with my dataset the following error occurs:

INFO:root:Loading model... INFO:root:Loaded model INFO:root:Loading data... 112 train files, 28 test files

TypeError Traceback (most recent call last)

in () 7 symbols = load_symbols(os.path.join(alphabet_directory, alphabet.value)) if alphabet.value else DEFAULT_ALPHABET 8 checkpoint_path = os.path.join(checkpoint_directory, dataset.value, checkpoint.value) if checkpoint.value else None ----> 9 train( 10 metadata_path=metadata, 11 dataset_directory=wavs, 3 frames /content/Voice-Cloning-App/training/tacotron2_model/stft.py in __init__(self, filter_length, hop_length, win_length, window) 67 # get window and zero center pad it to filter_length 68 fft_window = get_window(window, win_length, fftbins=True) ---> 69 fft_window = pad_center(fft_window, filter_length) 70 fft_window = torch.from_numpy(fft_window).float() 71 TypeError: pad_center() takes 1 positional argument but 2 were given I have tried different things but they don´t work. Can someone help me? I am new to coding in general (I only got into it specifically for this program) so I don´t really know how to properly troubleshoot Thx in advance
SandUhrGucker commented 1 year ago

I had the same error. pip install librosa==0.9.2 fixed that for me. For remote use in the colab, I added "librosa==0.9.2" to the code of the section Parameter Line 6