ttslearn.tacotron.gen.synthesis

ttslearn.tacotron.gen.synthesis(device, sample_rate, labels, acoustic_model, wavenet_model, _tqdm=<class 'tqdm.std.tqdm'>)[source]

Synthesize waveform

Parameters
  • device (torch.device) – device to use for computation (CPU or GPU).

  • sample_rate (int) – sample rate of the output waveform.

  • labels (list) – list of labels to generate.

  • acoustic_model (ttslearn.tacotron.models.Tacotron) – acoustic model.

  • wavenet_model (ttslearn.wavenet.WaveNet) – WaveNet vocoder.

  • _tqdm (optional) – tqdm progress bar.

Returns

waveform.

Return type

(torch.Tensor)