upskyy/ContextNet

PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INTERSPEECH 2020)

31
/ 100
Emerging

This project provides the core code for building advanced automatic speech recognition (ASR) systems. It takes raw audio data (or its pre-processed features) and transforms it into recognized text. It's intended for machine learning engineers or researchers who are developing and experimenting with cutting-edge speech-to-text models.

No commits in the last 6 months.

Use this if you are a machine learning engineer or researcher looking for a high-performance deep learning architecture to build and train custom speech-to-text models.

Not ideal if you need an out-of-the-box, ready-to-use speech recognition application without custom model development.

automatic-speech-recognition speech-to-text natural-language-processing machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

38

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Feb 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/upskyy/ContextNet"

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