teamtee/LLM-ASR-Error-Correction
This is a framework for using large language models to improve ASR recognition accuracy. You need to provide the recognized text and tag files to fill out the large model API.
This project helps speech recognition engineers or researchers improve the accuracy of their Automatic Speech Recognition (ASR) systems. It takes pre-recognized text files from an existing ASR system, uses a Large Language Model (LLM) to correct errors, and outputs refined, more accurate transcripts. This tool is for professionals focused on enhancing the precision of speech-to-text conversion.
No commits in the last 6 months.
Use this if you need to significantly reduce errors in transcripts generated by your current ASR system, leveraging the power of large language models.
Not ideal if you are looking for a standalone ASR system or don't have pre-recognized text outputs from an existing ASR pipeline.
Stars
14
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jun 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/teamtee/LLM-ASR-Error-Correction"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project