Is it possible to train on Google's TPU?
Training without language model
Has anyone successfully fine tuned a deepspeech mode?
How to distinguish speakers in conversation?
How to Strict the output to the Language Model only?
ARM native_client with GPU support
Building beta native client from source using recent TensorFlow version
What is the best/fast method to transcript 1K files?
Avoid adding information in tensorboard while validating or testing
Effect of various improvements on accuracy
WER and Loss increase when adding more data
docker build failed with error: error loading package 'native_client'
TUTORIAL : How I trained a specific french model to control my robot
Deepspeech recognition rate
Creating an Indian accent model with ~115k files
Distributed training set up of DeepSpeech code
Created an Arabic LM, but deepspeech is not learning, early stops
MFCC feature dimensions
Can we finetune from master with the 0.1.1 model?
Recommended hyperparameters range for fine tuning
How to create a mmap-able model from the output_graph.pb file
Will the results be different when use the trained model under "deepspeech" and "deepspeech-gpu"?
How to specify it to run on single/idle gpu only?
Uni-directional model for online/incremental ASR in real-time applications e.g. voice assistants
Why does adding the `--display_step 2` argument significantly slow down the training time?
Splitting the GPU memory to run multiple workers on a deepspeech server
Terminate called after throwing an instance of 'std::system_error'
run-cluster on multiple machines not working
Does anyone got a good result when training the Common Voice data set?
Problem including BatchNorm after Dense layers
← previous page
next page →