|
About the TTS (Text-to-Speech) category
|
|
1
|
2165
|
April 30, 2019
|
|
What are the TTS models you know to be faster than Tacotron?
|
|
63
|
2741
|
April 20, 2021
|
|
Empty sounds with LJS + GL
|
|
6
|
75
|
April 20, 2021
|
|
Mozilla Voice [ANSWERED]
|
|
3
|
141
|
April 14, 2021
|
|
Manual stress control with special symbol "+"
|
|
2
|
73
|
April 14, 2021
|
|
The model training is stuck at 1st epoch
|
|
6
|
111
|
April 13, 2021
|
|
Training 2 New Custom Datasets with TTS-recipes, need suggestions for inference/synthesis
|
|
1
|
56
|
April 12, 2021
|
|
CuDA cublasGemmEX failing at the beginning of the first epoch?
|
|
2
|
62
|
April 9, 2021
|
|
Generate Phonemes From Text
|
|
2
|
86
|
April 8, 2021
|
|
Does GST layer consider sequence length?
|
|
1
|
37
|
April 8, 2021
|
|
German grapheme to phoneme (g2p)
|
|
2
|
71
|
April 6, 2021
|
|
Contributing my german voice for tts
|
|
226
|
7523
|
April 4, 2021
|
|
Error while training tacotron with multigpu
|
|
1
|
44
|
April 2, 2021
|
|
🐸 Coqui.ai is here
|
|
4
|
539
|
April 2, 2021
|
|
All models stopped working for fine-tuning since coqui-ai
|
|
1
|
58
|
April 2, 2021
|
|
Running TTS on constrained hardware (+ no GPU)
|
|
40
|
3197
|
April 2, 2021
|
|
Robbie Williams - Feel
|
|
1
|
96
|
March 31, 2021
|
|
Tensorboard sample audio is dead air
|
|
1
|
48
|
March 30, 2021
|
|
How to use the TTS models
|
|
4
|
4639
|
October 29, 2019
|
|
Final results LPCNet + Tacotron2 (Spanish)
|
|
74
|
5084
|
January 11, 2021
|
|
How do you fine-tune a model for it to work with the tts / synthesize.py command?
|
|
2
|
92
|
March 29, 2021
|
|
Weekly TTS meetings
|
|
6
|
608
|
March 26, 2021
|
|
Anyone tried ONNX conversion?
|
|
1
|
52
|
March 24, 2021
|
|
Creating a Streaming Interface
|
|
3
|
88
|
March 24, 2021
|
|
Keep getting the same results when training
|
|
1
|
60
|
March 22, 2021
|
|
Any TTS Colabs that have models with northern English accents?
|
|
1
|
58
|
March 20, 2021
|
|
Guessing that this is over-fitting, but want to confirm
|
|
1
|
69
|
March 18, 2021
|
|
Attention weights of Graves Attention get decreased and reach zero value as iteration goes
|
|
13
|
432
|
March 16, 2021
|
|
Training with a 2GB GPU
|
|
37
|
572
|
March 14, 2021
|
|
Best model + vocoder combination for realistic speech generation
|
|
2
|
166
|
March 11, 2021
|
