xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
Built on a multilingual allophone system architecture from ICASSP 2020 research, it uses pretrained acoustic models that can be swapped (universal or language-specific) and supports language-specific phone inventory constraints to improve accuracy. Provides both command-line and Python APIs with automatic audio resampling, GPU acceleration support, and downloadable model variants—including a universal model covering 2000+ languages and specialized models for individual languages like English.
715 stars and 7,882 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
715
Forks
100
Language
Python
License
GPL-3.0
Category
Last pushed
Apr 26, 2024
Monthly downloads
7,882
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/xinjli/allosaurus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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
srvk/eesen
The official repository of the Eesen project
sooftware/kospeech
Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.