huckiyang/Interspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial
Interspeech Tutorial - Resource Efficient and Cross-Modal Learning Toward Foundation Modeling
This tutorial helps machine learning engineers and researchers adapt large, pre-trained speech and natural language processing models to new tasks more efficiently. It explains how to fine-tune these 'foundation models' using techniques like adapters and low-rank adaptation, reducing the computational resources needed. You'll learn how to take an existing massive model and customize it for specific applications like accent adaptation in text-to-speech or dialect identification, even with limited data or computing power.
No commits in the last 6 months.
Use this if you need to customize large pre-trained AI models for new speech or text tasks without retraining the entire model or requiring extensive computational resources.
Not ideal if you are looking for an off-the-shelf software tool for end-users, as this provides a technical deep-dive for AI practitioners rather than a ready-to-use application.
Stars
15
Forks
—
Language
—
License
—
Category
Last pushed
Oct 09, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/huckiyang/Interspeech23-Tutorial-Para-Efficient-Cross-Modal-Tutorial"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.