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