ttslearn.tacotron.gen.synthesis_griffin_lim¶
- 
ttslearn.tacotron.gen.synthesis_griffin_lim(device, sample_rate, labels, acoustic_model, scaler)[source]¶
- Synthesize waveform with Griffin-Lim algorithm. - 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. 
- scaler (sklearn.preprocessing.StandardScaler) – preprocessing scaler. 
 
- Returns
- waveform. 
- Return type
- (torch.Tensor)