|
Training TEDLIUM3 on AWS GPU(TESLA ) instance with 480GB RAM and 64 CPU
|
|
2
|
229
|
January 3, 2019
|
|
Default dropout rate 0.05 vs 0.2 used for training
|
|
6
|
480
|
January 2, 2019
|
|
Use Wikipedia to build language model - Issue with size of txt file
|
|
0
|
183
|
December 30, 2018
|
|
Has anybody here tried to develop a language model for Hindi/Nepali language?
|
|
2
|
354
|
December 22, 2018
|
|
Creating an Indian accent model with ~115k files
|
|
39
|
2486
|
December 21, 2018
|
|
Deepspeech.model is not found
|
|
12
|
452
|
December 21, 2018
|
|
If we join very small chunks of audio to create bigger chunks of acceptable size, do we need to keep in mind the integrety of the language being spoken for the language model to work properly?
|
|
3
|
206
|
December 21, 2018
|
|
Is latest models better than previous ones?
|
|
1
|
243
|
December 21, 2018
|
|
Running deepspeech for more .wav files to infer the text
|
|
3
|
1258
|
December 20, 2018
|
|
New v0.4-alpha.2 and language model
|
|
12
|
1992
|
December 19, 2018
|
|
Letter based language model
|
|
1
|
321
|
December 19, 2018
|
|
Distributed training
|
|
11
|
1229
|
December 17, 2018
|
|
Make the interface (more) functional
|
|
1
|
191
|
December 17, 2018
|
|
How to train Deepspeech model on google colab?
|
|
6
|
984
|
December 14, 2018
|
|
Cannot export trained model
|
|
3
|
346
|
December 14, 2018
|
|
DeepSpeech trained on the Maori Language
|
|
8
|
421
|
December 14, 2018
|
|
Running DeepSpeech inside Docker Container
|
|
10
|
1588
|
December 14, 2018
|
|
Impact of alignment of training data on model accuracy
|
|
0
|
172
|
December 14, 2018
|
|
Problem in Convergence - DeepSpeech not learning
|
|
13
|
584
|
December 13, 2018
|
|
Improving the accuracy of the speech recognition with newer iterations of deepspeech or other competing techniques in deep speech recognition!
|
|
5
|
910
|
December 7, 2018
|
|
Preemphasis value on processAudioWindow
|
|
1
|
146
|
December 7, 2018
|
|
Save the frozen model after every epoch
|
|
4
|
392
|
December 7, 2018
|
|
Building LM, noticed vocab.txt and librispeech-lm-norm.txt have a lot of low quality words
|
|
3
|
388
|
December 7, 2018
|
|
Unable to train model with default checkpoints and frozen model
|
|
6
|
790
|
December 7, 2018
|
|
Could not find unidirectional RNN
|
|
1
|
187
|
December 6, 2018
|
|
Inference hangs when running code in a Process
|
|
7
|
233
|
December 4, 2018
|
|
Why not convolution layers instead of hidden layers?
|
|
0
|
248
|
December 3, 2018
|
|
Decoding problem during test
|
|
3
|
270
|
December 2, 2018
|
|
How to get .pb model?
|
|
10
|
881
|
December 1, 2018
|
|
Where can I find cross compiling for aarch64?
|
|
59
|
1848
|
November 29, 2018
|
