kehanlu/DeSTA2

Code and model for ICASSP 2025 Paper "Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data"

39
/ 100
Emerging

This project offers a way for researchers and AI developers to create advanced speech language models (SLMs). It takes raw audio inputs and plain text instructions, then outputs intelligent, conversational responses about the audio content. This tool is for those building AI systems that can understand and respond to spoken language.

123 stars. No commits in the last 6 months.

Use this if you need to develop an AI model that can understand complex spoken commands and provide detailed, intelligent responses about audio content, without needing extensive speech instruction data.

Not ideal if you are an end-user simply looking for a ready-to-use voice assistant; this is a development tool for building such systems.

speech-recognition natural-language-processing conversational-ai audio-analysis ai-model-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

123

Forks

10

Language

HTML

License

Last pushed

Jul 15, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/kehanlu/DeSTA2"

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