yanghaha0908/FastHuBERT

Official implementation for Fast-HuBERT: An Efficient Training Framework for Self-Supervised Speech Representation Learning

32
/ 100
Emerging

This project helps researchers and developers accelerate the pre-training of self-supervised speech recognition models. It takes raw audio data or speech features as input and outputs a highly efficient, pre-trained speech representation model. Scientists and engineers working on speech processing applications, especially those constrained by computational resources, would use this.

No commits in the last 6 months.

Use this if you need to train self-supervised speech models significantly faster without compromising performance.

Not ideal if you are looking for a ready-to-use speech recognition system and are not involved in model training or research.

speech-recognition-research speech-model-training audio-processing computational-linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

97

Forks

4

Language

Python

License

MIT

Last pushed

Nov 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yanghaha0908/FastHuBERT"

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