|
Audio preprocessing
|
|
7
|
135
|
September 9, 2020
|
|
Expected Learning Rate When Training From Scratch
|
|
3
|
184
|
September 5, 2020
|
|
Data Requirements for Fine Tuning LJ Speech to learn my voice in English
|
|
2
|
133
|
September 1, 2020
|
|
Is there a tool that allows for desktop synthesis with these models?
|
|
4
|
166
|
August 22, 2020
|
|
Training DeepSpeech on Silence?
|
|
2
|
90
|
August 29, 2020
|
|
AttributeError: 'AttrDict' object has no attribute 'gst'
|
|
6
|
116
|
August 28, 2020
|
|
Noob need help with Mozilla TTS
|
|
4
|
141
|
August 26, 2020
|
|
One phoneme's pronunciation not matching dataset
|
|
9
|
230
|
August 25, 2020
|
|
Tacotron2: question about switching to BN prenet
|
|
1
|
125
|
August 18, 2020
|
|
Training a universal vocoder
|
|
26
|
389
|
August 18, 2020
|
|
Training suddenly dropping in quality
|
|
21
|
383
|
August 18, 2020
|
|
Fine-tuning Tacotron2 to new language
|
|
3
|
171
|
August 18, 2020
|
|
Fine-Tuning Trained Model to french Dataset
|
|
6
|
262
|
August 17, 2020
|
|
Pre-specified symbol embeddings
|
|
2
|
81
|
August 11, 2020
|
|
Length of sentences with DDC is shorter than with not
|
|
1
|
77
|
August 11, 2020
|
|
Additional ideas around dataset and TTS output testing
|
|
1
|
77
|
August 10, 2020
|
|
Example of healthy loss functions in Tacotron2 + Multiband Melgan?
|
|
7
|
229
|
August 9, 2020
|
|
Running TTS on constrained hardware (+ no GPU)
|
|
31
|
2034
|
August 6, 2020
|
|
Training universal PWGAN, background noise and bad output
|
|
14
|
200
|
August 5, 2020
|
|
Expected behaviour with LR in Vocoder training with --restore_path?
|
|
1
|
83
|
August 3, 2020
|
|
Recent experiments with DDC + other settings
|
|
3
|
234
|
August 2, 2020
|
|
Vocoder (dev) - potential memory usage issue in training?
|
|
15
|
271
|
August 2, 2020
|
|
What is the latest Colab Notebook / example on how to generate speech from text using Mozilla TTS?
|
|
3
|
222
|
July 30, 2020
|
|
LJspeech dataset audio improvements
|
|
7
|
124
|
July 28, 2020
|
|
Silences within utterances (not trailing)
|
|
3
|
109
|
July 28, 2020
|
|
[TWEB dataset] TestSentence audio is progressing while synthesized audio is noisy
|
|
2
|
95
|
July 28, 2020
|
|
My Tacotron test .wav is very long!
|
|
7
|
117
|
July 25, 2020
|
|
Is it possible to train a TTS model in a custom language (Latin) with only a couple hours of good quality training data
|
|
5
|
155
|
July 23, 2020
|
|
Using fatchord WaveRNN Model with TTS Tacotron
|
|
2
|
154
|
July 20, 2020
|
|
Mozilla TTS - how to save wav?
|
|
5
|
481
|
July 19, 2020
|
