Deep Speech

About the Deep Speech category (1)
How language model is used in deepspeech (4)
GPU much slower (9)
TUTORIAL : How I trained a specific french model to control my robot ( 2 3 ) (45)
ARM native_client with GPU support ( 2 ) (38)
Will you release a fully trained NN? (7)
Using Deep Speech ( 2 ) (22)
Material needed for FRENCH model creation ( 2 ) (31)
Printing periodic progress during training (2)
How much disk space is required for training Deepspeech model (17)
Deepspeech model (2)
Can we use DeepSpeech for Vietnamese Speech To Text? ( 2 ) (35)
How to make the testing process more quickly? (19)
Spanish Speech To Text: n_context meaning? (3)
When the model is exported during the training (2)
Next release (2)
Checkpoints for Online Learning (1)
What is the use of pre-built binaries (10)
Performance for native English speaker with pre-trained model? (14)
Creating An Online Environment To Train Specific Words (6)
‘pip install deepspeech’ doesn’t find a valid deepspeech on Linux Ubuntu 14.04.5 LTS. Kernel:Linux kanail 3.10.107-xenU-36-37a7b05-x86_64 (14)
Create A SubSet of existing models ( 2 ) (24)
What prediction information is available from deepspeech inference? (7)
Training from frozen graph vs checkpoints (4)
After Finishing training Optimization,What procedures will be executed,only the testing? (2)
Has anyone worked on streaming or online approach with DeepSpeech? (1)
DeepSpeech benchmarking / Shorten inference time (17)
Any Good Architecture for continous Inference (4)
Support for audios with background music (1)
Do we need to do any noice cancellation or pre-emphasis before feeding to deepspeech (2)