ai-adv-lab/deepspeech.mxnet

A MXNet implementation of Baidu's DeepSpeech architecture

46
/ 100
Emerging

Implements configurable RNN/LSTM/GRU architectures with batch normalization and Warp CTC loss for speech-to-text models, enabling network composition through JSON configuration files without code modification. Integrates SoundFile for audio preprocessing and TensorBoard for training visualization, supporting both training from scratch and checkpoint-based model resumption on MXNet's computational graph.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

83

Forks

33

Language

Python

License

Apache-2.0

Last pushed

May 20, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ai-adv-lab/deepspeech.mxnet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.