ictnlp/FastLongSpeech
FastLongSpeech is a novel framework designed to extend the capabilities of Large Speech-Language Models for efficient long-speech processing without necessitating dedicated long-speech training data.
This framework helps developers enhance Large Speech-Language Models (SLMs) to efficiently process long audio recordings without needing extensive long-speech training data. It takes an existing SLM and short-duration training data, and outputs a more capable SLM that significantly reduces computational effort and response time for tasks like transcription or understanding long conversations. This is for machine learning engineers or researchers building or deploying speech processing applications.
No commits in the last 6 months.
Use this if you need to improve the performance of Large Speech-Language Models on long audio inputs while minimizing training data requirements and computational overhead.
Not ideal if you are looking for an off-the-shelf application to transcribe or analyze long audio without any model training or development.
Stars
14
Forks
1
Language
Python
License
—
Category
Last pushed
Jul 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ictnlp/FastLongSpeech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase