VITA-Group/Audio-Lottery
[ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Zhangyang Wang
This helps speech application developers make their voice features run efficiently on mobile devices. It takes an existing, large speech recognition model and finds a much smaller, equally powerful version. This is for engineers and developers building speech-interactive apps who need to optimize for device performance and varied user environments.
No commits in the last 6 months.
Use this if you are developing mobile applications with speech recognition features and need to reduce the model size without sacrificing accuracy, even in noisy conditions.
Not ideal if you are looking for an off-the-shelf, ready-to-use speech recognition system without needing to optimize or customize the underlying models.
Stars
32
Forks
7
Language
Python
License
MIT
Category
Last pushed
Apr 08, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/VITA-Group/Audio-Lottery"
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