SiavashShams/ssamba

[SLT'24] The official implementation of SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model

44
/ 100
Emerging

This project helps audio engineers, researchers, and developers build better audio analysis systems. It takes raw audio recordings as input and produces high-quality, efficient audio representations (like numerical embeddings) that can then be used for tasks such as identifying sounds, recognizing speech, or analyzing emotional tone. The primary users are those who work with large volumes of audio data and need to extract meaningful insights.

134 stars.

Use this if you are developing or training machine learning models for audio tasks and need a robust, fast, and memory-efficient way to process raw audio into meaningful numerical data.

Not ideal if you are looking for a ready-to-use application to analyze audio without any programming or machine learning model development.

audio-analysis speech-recognition sound-classification audio-engineering acoustic-research
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

134

Forks

12

Language

Python

License

BSD-3-Clause

Last pushed

Nov 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/SiavashShams/ssamba"

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