iamjanvijay/rnnt_decoder_cuda
An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.
This project helps developers integrate a highly efficient speech-to-text decoding process into their applications. It takes raw speech audio features and a defined vocabulary, and rapidly produces the most probable text transcripts. It is designed for engineers building real-time speech recognition systems that demand fast and accurate transcription.
Use this if you are a software engineer or machine learning engineer building a production-level speech recognition system and need to quickly convert speech into text.
Not ideal if you are a non-developer seeking a ready-to-use speech-to-text application or a general-purpose natural language processing tool.
Stars
67
Forks
10
Language
Cuda
License
MIT
Category
Last pushed
Jan 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/iamjanvijay/rnnt_decoder_cuda"
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