dspavankumar/keras-kaldi

Keras Interface for Kaldi ASR

47
/ 100
Emerging

This project helps speech recognition engineers and researchers build and evaluate deep learning models for Automatic Speech Recognition (ASR). It takes in speech data and corresponding phonetic alignments, then produces trained deep neural networks (DNNs) or LSTMs for improved speech recognition. The models are compatible with Kaldi, a popular ASR toolkit.

122 stars. No commits in the last 6 months.

Use this if you are developing or experimenting with ASR systems and want to leverage Keras's deep learning capabilities with your existing Kaldi datasets and workflows.

Not ideal if you are looking for a ready-to-use, off-the-shelf ASR application without needing to build and train custom deep learning models.

Automatic Speech Recognition ASR Speech Processing Deep Learning Acoustic Modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

122

Forks

42

Language

Python

License

GPL-3.0

Last pushed

Sep 27, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dspavankumar/keras-kaldi"

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