AI engineering glossary · Generative media multimodal
What is RNN-T (RNN-Transducer)?
RNN-Transducer (also called RNN-T): A sequence model for streaming speech recognition that combines an audio encoder, a prediction network over previous outputs and a joint network. It can emit tokens as audio arrives, so it suits on-device and live captioning.
RNN-Transducer: an example
A phone keyboard's voice typing uses a transducer to show words as you speak rather than after you finish.
Related terms
- Connectionist temporal classification
- Streaming ASR
- Automatic speech recognition
More Generative media multimodal terms
- Sample rate
- Score distillation sampling
- Score-based generative model
- Short-time Fourier transform
- SigLIP
- Speaker diarisation
- Speaker embedding
- Spectrogram
Where you learn it
RNN-Transducer is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.