keithito / tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
MIT License
2.94k stars 965 forks source link

Sorry , I cannot reprocess the dataset,using thchs I cannot solve this problem. #315

Open Creiphyn opened 4 years ago

Creiphyn commented 4 years ago

Traceback (most recent call last): File "C:\Users\72970\Anaconda3\envs\tensorflow\lib\concurrent\futures\process.py", line 175, in _process_worker r = call_item.fn(*call_item.args, **call_item.kwargs) File "C:\Users\72970\Desktop\1\datasets\thchs30.py", line 74, in _process_utterance mel_spectrogram = audio.melspectrogram(wav).astype(np.float32) File "C:\Users\72970\Desktop\1\util\audio.py", line 66, in melspectrogram S = _amp_to_db(_linear_to_mel(np.abs(D))) - hparams.ref_level_db File "C:\Users\72970\Desktop\1\util\audio.py", line 143, in _linear_to_mel _mel_basis = _build_mel_basis() File "C:\Users\72970\Desktop\1\util\audio.py", line 149, in _build_mel_basis return librosa.filters.mel(hparams.sample_rate, n_fft, n_mels=hparams.num_mels, fmin=hparams.fmin, fmax=hparams.fmax) File "C:\Users\72970\Anaconda3\envs\tensorflow\lib\site-packages\librosa\filters.py", line 247, in mel lower = -ramps[i] / fdiff[i] ValueError: operands could not be broadcast together with shapes (1,2049) (0,)