Deep Speech


Topic Replies Created
Guideline for Specific Version of Deepspeech 15 January 11, 2019
Which Tensorflow, cuda 8 April 9, 2019
Common Voice dataset releases - Looking for your feedback 1 April 10, 2019
Preprocessing, Silence, Lyric Recognition 1 April 10, 2019
Tests on Deepspeech Python Package 2 April 10, 2019
Language Model Hyperparameter Optimisation 3 April 9, 2019
Training Vietnamese model 3 April 7, 2019
Cannot use deepspeech -e to get timestamp 2 April 9, 2019
Converting provided 0.4.1 english model to v0.5.0-alpha.5 1 April 8, 2019
Per word confidence 10 April 5, 2019
Validation loss plateus after some epochs 3 April 8, 2019
Getting better prediction accuracy during inshot-inference from checkpoint but less accuracy on trained model? 4 April 5, 2019
Generate Trie Issue 2 April 7, 2019
Retraining on my own data 9 April 3, 2019
Ghost char that is not in the dataset 24 March 18, 2019
Training fail with error about characters 7 April 3, 2019
Training does not resume from checkpoint. Always restarts from epoch 0 3 April 6, 2019
Trouble running compiled native client from master 7 April 4, 2019
Where is Vocab.txt file? 11 April 2, 2019
Training Chinese model 20 April 17, 2018
AttributeError: module 'tensorflow' has no attribute 'app' 4 January 28, 2019
Train 1 epoch take too much time 2 April 3, 2019
ResourceExhaustedError *after* training an epoch + performing dev set evaluation 5 February 16, 2019
Google's On-Device Speech Recognizer 22 March 13, 2019
Python Package for Windows 14 December 1, 2017
How to use nuget package in Windows? 7 April 1, 2019
Online Decoding (since v2) 12 April 1, 2019
How can i improve Indian accent accuracy for pretrained model v0.2.0.? 14 September 21, 2018
Multi-Machine Distributed Training issue 4 March 30, 2019
Error when run generate trie 8 March 31, 2019