Error while running sample model on Raspbian GNU/Linux 9.4 (stretch)
Custom Model created by me has a small size
Decoding for proper nouns(human names)
Cleaning Transcript Files (Invalid label when building trie)
LSTM vs. GRU
Can we use DeepSpeech for Vietnamese Speech To Text?
Doesn`t use GPU while training, but during recognition it uses one
Can I use other language modelling tools than KenLM
How to modify this code to output multi-candidate results by beam search？
Produce lattices or n-bests instead of just one best
Training issues and completion time
Not able to buld native client from source
How to go about creating this to work with indian accent english
Text produced has long strings of words with no spaces
Unable to run deepspeech
Lesser illegible outputs by decreasing the size of the context window (?)
Support for batch STT
Support for batch STT?
Error while running taskcluster.py
How can the the model outputs multiple candidates when decoding?
Cannot find deepspeech binaries compatible with tensorflow 1.6 to run inference on a trained model
Training a model at 8khz?
Converting pre-trained model into TensorFlow "Saved_Model" format?
DeepSpeech cloud architecture
Native_client/deepspeech_utils.so - undefined reference to symbol 'roundf@@GLIBC_2.2.5'
Another pip installation question, not finding solution that works
InvalidArgumentError at validating step
Training - test set is run on CPU with a single thread
Run Model on Server that only supports Tensorflow 1.3
DeepSpeech native client compilation for Asus Thinkerboard
← previous page
next page →