Deep Speech


Deep speech performance is not good with my training (1)
Process finished with exit code 134(interrupted by signal 6:SIGABRT) (1)
Word timestamps (1)
Deepspeech silence detection (3)
Can we use for Vietnamese Speech? (2)
[Solved] int() argument must be a string, a bytes-like ofject or a number, not ´NoneType´ (3)
[Solved] Unable to train from frozen model - " Requested return_element 'lstm_fused_cell/kernel:0' not found in graph_def." (3)
DeepSpeech Accuracy Issues and Newbie Questions (7)
Inference troubles - Not found: Op type not registered 'BlockLSTM' (3)
How does the LM used to update model parameter? (3)
Gibberish inference result for GSM audio (2)
Cannot resolve a new error after updating native client (5)
Working Deepspeech on Cuda 9.0 and Cudnn 7.0.5 (3)
Different outputs when using DeepSpeech as python library (5)
Why is the output.pb file almost half a gig and how wide is the input layer? (2)
Unable to run deepspeech GPU version with CUDA 9 (6)
Issue with building release version 0.1.1 DeepSpeech and Tensorflow (5)
Longer audio files with Deep Speech (9)
Global step not increased (3)
Information on training and inferring audio file length (6)
Missing libdeepspeech_utils.so (9)
How to install specific native_client version from taskcluster (11)
Conversational speeches as training data (2)
Language Model Creation (12)
System requirements for training Indian accent English over DeepSpeech pre-trained model checkpoints? (20)
Best way to get a baseline WER with the pre-trained model on my own test set (1)
Is it possible to train on Google's TPU? (3)
Training without language model (4)
Has anyone successfully fine tuned a deepspeech mode? (5)
How to distinguish speakers in conversation? (3)