|
Unable to run deepspeech GPU version with CUDA 9
|
|
5
|
925
|
August 17, 2018
|
|
Issue with building release version 0.1.1 DeepSpeech and Tensorflow
|
|
4
|
379
|
August 16, 2018
|
|
Global step not increased
|
|
2
|
908
|
August 15, 2018
|
|
Information on training and inferring audio file length
|
|
5
|
409
|
August 15, 2018
|
|
Missing libdeepspeech_utils.so
|
|
8
|
644
|
August 14, 2018
|
|
How to install specific native_client version from taskcluster
|
|
10
|
760
|
August 14, 2018
|
|
Conversational speeches as training data
|
|
1
|
279
|
August 13, 2018
|
|
Best way to get a baseline WER with the pre-trained model on my own test set
|
|
0
|
241
|
August 9, 2018
|
|
Training without language model
|
|
3
|
518
|
August 1, 2018
|
|
Has anyone successfully fine tuned a deepspeech mode?
|
|
4
|
673
|
August 1, 2018
|
|
How to distinguish speakers in conversation?
|
|
2
|
338
|
July 30, 2018
|
|
How to Strict the output to the Language Model only?
|
|
6
|
616
|
July 29, 2018
|
|
ARM native_client with GPU support
|
|
54
|
3084
|
July 27, 2018
|
|
Building beta native client from source using recent TensorFlow version
|
|
7
|
291
|
July 26, 2018
|
|
What is the best/fast method to transcript 1K files?
|
|
3
|
324
|
July 26, 2018
|
|
Avoid adding information in tensorboard while validating or testing
|
|
2
|
230
|
July 26, 2018
|
|
Effect of various improvements on accuracy
|
|
5
|
289
|
July 25, 2018
|
|
WER and Loss increase when adding more data
|
|
4
|
448
|
July 25, 2018
|
|
docker build failed with error: error loading package 'native_client'
|
|
3
|
287
|
July 24, 2018
|
|
Deepspeech recognition rate
|
|
16
|
4126
|
July 23, 2018
|
|
Distributed training set up of DeepSpeech code
|
|
8
|
823
|
July 20, 2018
|
|
MFCC feature dimensions
|
|
2
|
439
|
July 16, 2018
|
|
Can we finetune from master with the 0.1.1 model?
|
|
0
|
191
|
July 16, 2018
|
|
Recommended hyperparameters range for fine tuning
|
|
3
|
639
|
July 11, 2018
|
|
Will the results be different when use the trained model under "deepspeech" and "deepspeech-gpu"?
|
|
5
|
552
|
July 11, 2018
|
|
How to specify it to run on single/idle gpu only?
|
|
9
|
344
|
July 11, 2018
|
|
Uni-directional model for online/incremental ASR in real-time applications e.g. voice assistants
|
|
2
|
387
|
July 10, 2018
|
|
Why does adding the `--display_step 2` argument significantly slow down the training time?
|
|
7
|
384
|
July 10, 2018
|
|
Splitting the GPU memory to run multiple workers on a deepspeech server
|
|
9
|
1252
|
July 9, 2018
|
|
Terminate called after throwing an instance of 'std::system_error'
|
|
18
|
3136
|
July 9, 2018
|
