Deep Speech


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)
How to Strict the output to the Language Model only? (7)
ARM native_client with GPU support ( 2 3 ) (55)
Building beta native client from source using recent TensorFlow version (8)
What is the best/fast method to transcript 1K files? (4)
Avoid adding information in tensorboard while validating or testing (3)
Effect of various improvements on accuracy (6)
WER and Loss increase when adding more data (5)
docker build failed with error: error loading package 'native_client' (4)
TUTORIAL : How I trained a specific french model to control my robot ( 2 3 4 ) (73)
Deepspeech recognition rate (17)
Creating an Indian accent model with ~115k files ( 2 ) (39)
Distributed training set up of DeepSpeech code (9)
Created an Arabic LM, but deepspeech is not learning, early stops (2)
MFCC feature dimensions (3)
Can we finetune from master with the 0.1.1 model? (1)
Recommended hyperparameters range for fine tuning (4)
How to create a mmap-able model from the output_graph.pb file (12)
Will the results be different when use the trained model under "deepspeech" and "deepspeech-gpu"? (6)
How to specify it to run on single/idle gpu only? (10)
Uni-directional model for online/incremental ASR in real-time applications e.g. voice assistants (3)
Why does adding the `--display_step 2` argument significantly slow down the training time? (8)
Splitting the GPU memory to run multiple workers on a deepspeech server (10)
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)