iamjanvijay/rnnt_decoder_cuda
An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.
Optimized prefix beam search decoder for RNN-Transducer models, achieving ~100ms decoding latency for 5-second audio segments at beam size 10. Implements the full transduction algorithm in CUDA-accelerated C++, enabling real-time inference on GPU hardware. Supports configurable beam widths and vocabulary sizes, making it suitable for production speech recognition pipelines requiring low-latency online decoding.
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....
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
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