Deep Speech


Terminate called after throwing an instance of 'std::system_error' (19)
run-cluster on multiple machines not working (1)
Does anyone got a good result when training the Common Voice data set? (5)
Problem including BatchNorm after Dense layers (1)
Training v.0.1.1. Frozen Graph with Tensorflow 1.4 (3)
Hardware required for Deespeech Training (3)
DeepSpeech generates long nonsense tokens as output (2)
Increasing --train_batch_size 2 to --train_batch_size 3 causes DeepSpeech not to train anymore. Why? (6)
What does the "Test of Epoch [number]" mean? (3)
Training Common Voice issue: Invalid argument: Labels length is zero in batch 0 (10)
Standalone WER script? (7)
Running deepspeech for more .wav files to infer the text (2)
How to train with other languages (9)
Case sensitive recognition of names, cities, etc (2)
What are the training data sets of the future release of pre-trained model 0.2 or 0.3? (2)
One model per accent or one model for all accents? (3)
Unable to get training to work - permission error (2)
LM + TRIE performance (14)
Which deepspeech version uses Tensforflow version 1.6? (4)
Gibberish inference result when using pre-trained model for unknown distribution (7)
Creation of language model and trie (18)
applying the model on a set of audio files (4)
Tensorflow import and deepspeech.model import failing (6)
WARNING:tensorflow:It seems that global step (tf.train.get_global_step) has not been increased (8)
Problems when I try test my model in deep speech (5)
When the model is exported during the training (5)
Loss function appears to slowly climb over batches during epoch, reset every epoch (3)
Pretrained acoustic model as Feature extractor (1)
Decoding time of 30 second audio file (2)
How do I train a model using transfer learning? (6)