|
How to use analysis_dataset.py?
|
3
|
April 30, 2020
|
|
Error when trying to generate speech with self-contained package
|
1
|
April 28, 2020
|
|
ImportError: cannot import name 'BCELossMasked'
|
1
|
April 27, 2020
|
|
Sample Generation Rate for WaverRNN
|
1
|
April 27, 2020
|
|
Using custom trained WaveRNN models
|
4
|
April 27, 2020
|
|
Partial caching of generated speech
|
3
|
April 24, 2020
|
|
[Help Wanted] Please share your trained TTS models
|
3
|
April 24, 2020
|
|
[WaveRNN]ValueError: all input arrays must have the same shape
|
4
|
April 22, 2020
|
|
Error when trying to use custom trained wavernn model
|
4
|
April 21, 2020
|
|
UnboundLocalError: local variable 'mel_input' referenced before assignment
|
4
|
April 20, 2020
|
|
A test Sentence for LJSpeech Tacotron1 model
|
1
|
April 20, 2020
|
|
Train Multispeaker Dataset + WaveRNN
|
35
|
April 18, 2020
|
|
How to use AttentionEntropyLoss?
|
4
|
April 16, 2020
|
|
Docker missing espeak
|
5
|
April 15, 2020
|
|
RuntimeError: CUDA out of memory. after the first epoch with custom dataset
|
4
|
April 15, 2020
|
|
Mozilla TTS output voice still sounds robotic after almost 400K
|
3
|
April 14, 2020
|
|
-closed due to no respond-
|
1
|
April 7, 2020
|
|
Two questions about Multi Speaker models
|
4
|
April 7, 2020
|
|
LibrtiTTS, phonemizer and punctuation
|
4
|
April 7, 2020
|
|
TestFigures doesn't align
|
27
|
April 6, 2020
|
|
Error while attempting to train WaveRNN
|
3
|
April 6, 2020
|
|
Training a TTS model with a language that doesn't have a supported phoneme_language
|
4
|
March 30, 2020
|
|
Text-to-speech output, words are getting duplicated
|
2
|
March 27, 2020
|
|
Synthetic test sentence TypeError: bad operand type for abs(): 'NoneType' error
|
2
|
March 26, 2020
|
|
Anyone interested in Tensorflow 2.X based TTS using Eager Mode?
|
3
|
March 24, 2020
|
|
Dev branch on LJSpeech pronunciation of 'echo'
|
2
|
March 23, 2020
|
|
Can eSpeak transcription cause training/testing difficulties?
|
8
|
March 21, 2020
|
|
Transfer Learning / Model Refinement to change LJSpeech
|
6
|
March 20, 2020
|
|
My latest results using private dataset trained Tacotron2 model with MelGAN vocoder
|
10
|
March 20, 2020
|
|
WaveRNN trained result sound strange
|
9
|
March 20, 2020
|
