Mozilla TTS


Topic Replies Activity
[UPDATE] Released Speaker Encoder 1 November 1, 2019
Shape mismatch for mel_input and decoder_output 2 November 1, 2019
When I use synthesis.py files to synthesize audio,how to remove the mute part without do_trim_silence=True? #306 5 October 26, 2019
How to use the TTS models 4 October 29, 2019
Different max_decoder_steps in both Tacotron and Tacotron2 2 October 22, 2019
Need help on Tacotron2 assertion error on wav file 2 October 24, 2019
Error when running colab notebook 1 October 22, 2019
Sharing my 19h of single speaker (Spanish) 1 October 12, 2019
Language "zh" is not supported by the EspeakBackend.name 2 October 5, 2019
Install fails when installing matplotlib 2 October 4, 2019
Tacotron1 Deployment on t2.large 4 October 3, 2019
Distributed training: optimal parameters 23 October 2, 2019
Could Lingua Libre be a source of training data 1 October 2, 2019
Any instructions on how to resume training from a checkpoint? 3 October 2, 2019
Any step by step how-to/documentation on synthesizing with a pre-trained model? 4 September 25, 2019
Audio amplitude was clipped 😱 1 September 25, 2019
Difficult words manual stress control 4 September 25, 2019
Any plans for SSML, prosody control; GST 1 September 24, 2019
Weekly TTS meetings 3 September 23, 2019
Tip for improving voice naturalness: review power parameter (again) 5 September 23, 2019
Sharing my 100h of single speaker (Spanish) 7 September 20, 2019
Hangs on dist.init_process_group in distribute.py 3 September 19, 2019
Query regarding post processing 50 September 19, 2019
Radam optimizer 4 September 18, 2019
My progress on expressive speech synthesis 5 September 18, 2019
RuntimeError: Error(s) in loading state_dict for Tacotron 1 September 6, 2019
Pretrained model for Multiple Speaker Embedding 2 September 5, 2019
Standard for new Dataset 2 September 5, 2019
?!. question mark and others in the dataset 2 August 30, 2019
Abbreviation in the dataset. Is it gonna work? 4 August 29, 2019