efeslab/LiteASR
[EMNLP Main '25] LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
This project helps operations engineers and developers deploy powerful automatic speech recognition (ASR) systems, like OpenAI's Whisper, more efficiently. It takes an existing Whisper model and compresses its core processing component, leading to faster transcription of audio files with minimal loss in accuracy. This is ideal for those managing ASR infrastructure or building speech-enabled applications.
148 stars. No commits in the last 6 months.
Use this if you need to run high-quality speech-to-text transcription faster or on devices with limited computational power, without significantly compromising accuracy.
Not ideal if you are a casual user simply looking to transcribe a few audio files without needing to optimize system performance or manage model deployment.
Stars
148
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
May 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/efeslab/LiteASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition