upskyy/Transformer-Transducer

PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASSP 2020)

43
/ 100
Emerging

This project offers a specific architecture for building streaming automatic speech recognition (ASR) systems. It takes raw audio features and processes them to generate text transcriptions in real-time. It's designed for machine learning engineers and researchers who are building and evaluating advanced speech-to-text models.

113 stars. No commits in the last 6 months.

Use this if you are a machine learning engineer working on developing or enhancing real-time speech recognition models and want to incorporate a Transformer-based architecture.

Not ideal if you are looking for a complete, out-of-the-box speech-to-text application or a solution that handles the entire training pipeline.

speech-to-text automatic-speech-recognition real-time-transcription machine-learning-engineering audio-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

113

Forks

20

Language

Python

License

Apache-2.0

Last pushed

Feb 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/upskyy/Transformer-Transducer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.