Mozilla TTS


Topic Replies Activity
About the Mozilla TTS category 1 April 30, 2019
Tacotron 1+ LibriTTS multispeaker model 10 May 27, 2020
I cannot get PWGan to converge/sound good 3 May 24, 2020
How to start with TTS + WaveRNN? 11 May 22, 2020
TTS v0.0.2 released 1 May 22, 2020
Tensorboard weird artefact on ground truth spectrogram 4 May 22, 2020
Multiple voices dataset 4 May 22, 2020
Training hardware bottlenecks 18 May 22, 2020
Can we use the pretrained models on the original PWGan repo? 18 May 18, 2020
Which are the right commit versions for the Benchmark.ipynb notebook? 4 May 19, 2020
Trouble with WaveRNN universal vocoder model 2 May 18, 2020
Portuguese TTS model 8 May 18, 2020
Running TTS on constrained hardware (+ no GPU) 26 May 17, 2020
ForwardTacotron experience 13 May 16, 2020
Is there any way to enable GST learning on Taco2? 8 May 15, 2020
What is the cause of this noise? 5 May 15, 2020
Attention makes repetitions after long training (after converging successfully) 5 May 15, 2020
[WaveRNN]RuntimeError: cuda runtime error (59) : device-side assert triggered 5 May 14, 2020
[UPDATE] Released Speaker Encoder 3 May 13, 2020
Contributing my german voice for tts 99 May 12, 2020
Odd memory error 450 epochs in 15 May 11, 2020
[Private dataset - Portuguese] Expecting healthier results at 10k+ steps 14 May 8, 2020
What is the difference between extractring spectro's from TTS and preprocess_data.py? 1 May 8, 2020
Emotional Text to Speech 9 May 7, 2020
Failing to synthesize when using GravesAttention 1 May 4, 2020
Multispeaker development progress 30 May 5, 2020
C++ Implementation of synthesizer for the Tacotron model based on OpenCV capable of running on mobile devices 11 May 5, 2020
GPL in the way!? License issues regarding current source code? 7 May 5, 2020
[FEATURE REQUEST] Argument "--use_cuda" in synthesize.py: not working or not as expected!? 3 May 4, 2020
Stop loss spikes 8 May 4, 2020