dangvansam/viet-asr

VietASR - Vietnamese Automatic Speech Recognition

61
/ 100
Established

Implements QuartzNet architecture via NVIDIA NeMo with language model decoding using KenLM for improved accuracy. Trained on ~100 hours of Vietnamese speech (YouTube, radio, call center, TTS, and public datasets), the compact 13M-parameter model achieves fast inference. Offers both batch audio transcription and a Flask web application, with an active PyTorch-based v2.0 branch in development.

165 stars.

No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

165

Forks

56

Language

Python

License

Apache-2.0

Category

end-to-end-asr-frameworks

Last pushed

Mar 18, 2026

Commits (30d)

0

GitHub
End-to-End ASR Frameworks · 109 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dangvansam/viet-asr"

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....

69

xinjli/allosaurus

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages

65

wenet-e2e/wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

57

srvk/eesen

The official repository of the Eesen project

51

sooftware/kospeech

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition leveraging PyTorch and Hydra.

51

Explore Voice AI Tools

All categories Trending Voice AI directory Insights