Which deepspeech version uses Tensforflow version 1.6?
Gibberish inference result when using pre-trained model for unknown distribution
Creation of language model and trie
applying the model on a set of audio files
Tensorflow import and deepspeech.model import failing
Error when running inference on an audio file
WARNING:tensorflow:It seems that global step (tf.train.get_global_step) has not been increased
Problems when I try test my model in deep speech
When the model is exported during the training
Loss function appears to slowly climb over batches during epoch, reset every epoch
Unable to run deepspeech GPU version with CUDA 9
Pretrained acoustic model as Feature extractor
Decoding time of 30 second audio file
How do I train a model using transfer learning?
Using Deep Speech
Add support for a new language
Low WER on Switchboard with DeepSpeech pretrained model
Interesting blog post on the importance of training data quality
How could I apply transfer learning on pre trained model?
Help with understanding benchmarks - are we at 5.6% word error rate on Librespeech Clean+Other?
Is it OK if all jobs are on worker:0?
Error during trie creation
Unable to run inference on trained model
Any documentation around the tensorboard outputs?
How exactly the decoder (and especially tf.nn.ctc_beam_search_decoder) works?
Illegal Instruction error on Rasberry Pi
Training parameters for Librispeech-clean dataset
Training Chinese model
← previous page
next page →