iamjanvijay/rnnt_decoder_cuda

An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.

44
/ 100
Emerging

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.

speech-recognition real-time-transcription voice-ai audio-processing
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

67

Forks

10

Language

Cuda

License

MIT

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.