awslabs/speech-representations

Code for DeCoAR (ICASSP 2020) and BERTphone (Odyssey 2020)

40
/ 100
Emerging

This project helps speech scientists and researchers create detailed numerical representations from raw audio. You provide speech recordings (WAV files), and it outputs specialized feature vectors that capture acoustic information. These outputs are crucial for training and evaluating advanced speech recognition, speaker identification, and language detection systems.

104 stars. No commits in the last 6 months.

Use this if you need to extract high-quality, contextualized acoustic features from speech audio for use in machine learning models.

Not ideal if you are looking for a fully maintained toolkit for training and fine-tuning these models, as this repository is not actively updated.

speech-recognition speaker-identification language-detection acoustic-analysis audio-feature-extraction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

104

Forks

14

Language

Python

License

Apache-2.0

Last pushed

Nov 26, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/awslabs/speech-representations"

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