HarunoriKawano/BEST-RQ

Implementation of the paper "Self-supervised Learning with Random-projection Quantizer for Speech Recognition" in Pytorch.

35
/ 100
Emerging

This project helps machine learning researchers working on speech technology by providing a PyTorch implementation of a method for self-supervised speech recognition. It takes raw audio data and processes it into discrete units suitable for training robust speech recognition models, reducing the need for extensive labeled data. The ideal user is an ML researcher or engineer developing advanced speech recognition systems.

No commits in the last 6 months.

Use this if you are a machine learning researcher developing speech recognition systems and want to experiment with or apply a specific self-supervised learning technique for improved model performance.

Not ideal if you are looking for an off-the-shelf speech recognition application or a pre-trained model for immediate use without deep technical integration.

speech-recognition self-supervised-learning audio-processing machine-learning-research deep-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

91

Forks

7

Language

Python

License

Apache-2.0

Last pushed

May 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/HarunoriKawano/BEST-RQ"

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