Deep Speech


DeepSpeech native client compilation for Asus Thinkerboard (20)
Julius speech models based on Mozilla corpus (5)
Replacing non ascci characters when process corpus does not replace for the nearest character (8)
Loss Not Reducing (6)
Libctc_decoder_with_kenlm.so: cannot open shared object file (3)
Language model compilation (3)
Unable to load pre-trained model (16)
Data augmentation slowing training (4)
Pip install deepspeech throws error while serving model trained on TF 1.6 (3)
Improving accuracy with 8khz audio? (7)
How can I use my model? (4)
Recognizing phone numbers (2)
Val loss stops going down after 6 epochs (4)
Inference time run speeds (1)
TypeError: 'sess' must be a Session; (6)
Is a trained DeepSpeech AI model subject to MPL2? (3)
Offline speech recognition on mobile (3)
TV speech recognition (3)
How can I train a model without a language model? (2)
Feed additional inputs to the model (4)
Error with sample model on Raspbian Jessie ( 2 ) (31)
Number of trainable parameters in the frozen network (1)
Built native-client from source for CPU only uses one thread (7)
How to build gpu version from source (18)
Trying to train own model using native_client getting error - libctc_decoder_with_kenlm.so: undefined symbol (15)
Access activations of the neurons (12)
how to build native_client with tensorflow 1.5 and cuda8 (2)
InvalidArgumentError when using do_single_file_inference() (3)
Very high error rate for this audio clip with my own model (7)
Unable to train model with default checkpoints and frozen model (6)