WaveRNN
WaveRNN copied to clipboard
fatchord
WaveRNN Vocoder + TTS
Trying to set up the project for the first time by following the instructions didn't work, some dependencies were incorrect. After messing with them I eventually found a combination that...
Hello, thank you very much for the work, I just have a question. How can I convert the Tacotron 2 model to onnx?
I didn't see any audio files or audio file path that have been used to generate the text any idea about that? Thanks! 😄
text_dict = ljspeech(path) with open(f'{paths.data}text_dict.pkl', 'wb') as f: pickle.dump(text_dict, f) ======================================================== i commented the above out in preprocess.py. then the following happened ========================================================= D:\projects\anacanda-voice-project\WaveRNN-master\WaveRNN-master>python preproce ss.py --path witch-wife_2010_librivox File "preprocess.py",...
Hello, I reinstalled setuptools (same version. 17.0) and now I get an error I haven't gotten before. ``` WaveRNN\models\fatchord_version.py", line 258, in generate output[-20 * self.hop_length:] *= fade_out ValueError: operands...
Fixes issue in writing to .WAV file. Modern librosa no longer supports write_wav(), soundfile seemed like the straightforward solution.
"librosa.output" was removed in librosa version 0.8.0. This is documented in [their changelog](https://librosa.org/doc/latest/changelog.html?highlight=output#v0-8-0) ****** F:\【密】AI-人工智能\WaveRNN>python quick_start.py Using device: cpu Initialising WaveRNN Model... Trainable Parameters: 4.234M Initialising Tacotron Model... Trainable Parameters:...
This set of requirements worked for me in Google Colab. You might want to take a second look at the right set of requirements, this feels fairly ad-hoc. But it...
I would like to know why do you minus 2 in preprocessing ? https://github.com/fatchord/WaveRNN/blob/3595219b2f2f5353f0867a7bb59abcb15aba8831/utils/dataset.py#L69 and you have `+ 2 * hp.voc_pad` in `mel_win`, why `+ 2 * hp.voc_pad` again here?...
