Deep Speech


Retraining for poorer-quality audio (4)
How to handle out of vocabulary words (1)
How to create a mmap-able model from the output_graph.pb file (13)
Native_client to inference a model trained in v0.1.1 (2)
Mismatch in sizes of generated files and the original ones (1)
Fine Tuning Language Model (7)
Training data for fine tuning the acoustic model (2)
Pretrained Model cannot provide accurate English words (19)
Preprocessing step taking a long time (3)
How to do Contact Name Recognition using DeepSpeech (4)
generate_tri invald label (3)
About beam_search with KenLM (1)
Citing Deep Speech (3)
ARM arch taskcluster native client package not including libctc_decoder_with_kenlm.so (14)
./bin/run-ldc93s1.sh fails (3)
DeepSpeech halts after initialising tensorflow devices [solved] (2)
Common Voice training data stats (6)
Question regarding custom language model (12)
Implementing streaming speech recognition using C++ (3)
Information on pre-trained Models (14)
How to know exact word time using deepspeech (10)
Fine tuning a model (3)
How to use a pretrained model with my own training data (4)
Does the pre-trained model use CommonVoice data? (5)
Displaying WER result of Training Set takes long time (2)
Deep Speech 2 training the data on top of the pre trained model (4)
Can Mean Edit Distance be thought of as Character Error Rate? (1)
Format of Vocabulary file for creating trie (4)
Benchmark results with v0.3.0? (5)
DeepSpeech Tensorflow does not use all CPU cores (13)