Deep Speech


Can I use pre-trained model with DeepSpeech.py? (8)
Text produced has long strings of words with no spaces (15)
Web service support for speech to text engine (3)
Developing ad-hoc STT and TTS systems (3)
Deepspeech project roadmap (3)
How to tune alpha (lm_weight) and beta(word_count_weight) for our custom training set? (3)
Training sample size (2)
Setting up training pipe for MacOS (2)
Question about how to make a prediction (4)
What is the training set of the pre-trained model? (17)
Why are the words combined when we use language model (3)
Quality of the CTC decoder / limit inference words to known words only (6)
About the utilization of CPU and GPU (2)
Using Deep Speech (20)
Will the results be different when use the trained model under "deepspeech" and "deepspeech-gpu"? (2)
How to test deepspeech on my computer? (5)
Client.py Error - No Module names _model (3)
How does DeepSpeech discriminate between speech-music? (3)
Role of LM while training (2)
Is the language model based on character or word? (2)
Customizing language model (12)
Will you release a fully trained NN? (5)
How to prepare training data and test data for deepspeech speech to text (2)
Phonemes Conversion (8)
Installation frustrations (7)
Audacity VAMP plugin for Deep Speech (6)
Inference error (3)
KenLM Word Prediction (2)
ARM native_client with GPU support (8)
Built native client from scratch, accuracy issues (4)