|
The challenges of aligning spoken word to text unobserved
|
|
7
|
769
|
January 8, 2021
|
|
Words are being mumbled, audio files end with a hissing sound
|
|
6
|
654
|
January 3, 2021
|
|
What makes models compatible?
|
|
5
|
328
|
January 3, 2021
|
|
German Karlsson Models and Notebook
|
|
11
|
973
|
December 23, 2020
|
|
Loss spikes and does not go down on LJ Speech
|
|
5
|
657
|
December 23, 2020
|
|
Best place to start with TTS in general
|
|
7
|
558
|
December 21, 2020
|
|
Incremental TTS idea (with accompanying paper)
|
|
3
|
379
|
December 21, 2020
|
|
Tacotron training error: Mean-Var stats does not match the given feature dimensions
|
|
5
|
1233
|
December 20, 2020
|
|
About model training, vocoder training and dataset error handling
|
|
4
|
926
|
December 20, 2020
|
|
What is the right way to take advantage of a german model with train_tts.py?
|
|
18
|
774
|
December 19, 2020
|
|
Creating a github page for hosting community trained models
|
|
19
|
1368
|
December 17, 2020
|
|
Sentences which trigger an endless loop
|
|
11
|
1326
|
December 17, 2020
|
|
When mozilla tts will be in firefox?
|
|
4
|
1483
|
December 16, 2020
|
|
Gruut discussions
|
|
11
|
1706
|
December 16, 2020
|
|
Noise in audio files
|
|
3
|
350
|
December 14, 2020
|
|
Tacotron 2 & FP16
|
|
6
|
1060
|
December 12, 2020
|
|
Fine-Tune speaker-encoder on own data. Is it worth it?
|
|
12
|
1408
|
December 12, 2020
|
|
Tacotron2 and multiband-melgan as vocoder
|
|
5
|
863
|
December 12, 2020
|
|
Untrained Vocoder Question
|
|
4
|
357
|
December 9, 2020
|
|
--continue__path on vocoder training seems to bump up all loss values
|
|
7
|
484
|
December 9, 2020
|
|
Universal / multi-speaker vocoders
|
|
8
|
1551
|
December 8, 2020
|
|
Using tensorboard.dev
|
|
3
|
673
|
December 5, 2020
|
|
Stopnet loss got high and not reducing / dataset change
|
|
9
|
748
|
December 5, 2020
|
|
Fine-Tune on a different coarse_decoder reduction ratee
|
|
6
|
501
|
December 4, 2020
|
|
Basic Cleaners or Phoneme Cleaners
|
|
2
|
1575
|
December 2, 2020
|
|
Do we need to change symbols when using phonemic text as input?
|
|
6
|
1112
|
December 2, 2020
|
|
Size mismatch for decoder.stopnet.1.linear_layer.weight: copying a param with shape torch.Size([1, 1584]) from checkpoint, the shape in current model is torch.Size([1, 1104])
|
|
3
|
3471
|
November 29, 2020
|
|
UnicodeDecodeError
|
|
2
|
242
|
November 25, 2020
|
|
ModuleNotFoundError: No module named 'TTS.utils.radam'
|
|
6
|
1936
|
November 24, 2020
|
|
Speaker encoder used with release MultiTTS models
|
|
2
|
765
|
November 20, 2020
|
