4 papers · 1 filter
Chunk-wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text
Hainan Xu, Vladimir Bataev, Travis M. Bartley +1
We propose Chunk-wise Attention Transducer (CHAT), a novel extension to RNN-T models that processes audio in fixed-size chunks while employing cross-attention within each chunk. Th…
WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection
Hainan Xu, Vladimir Bataev, Lilit Grigoryan +1
We propose Windowed Inference for Non-blank Detection (WIND), a novel strategy that significantly accelerates RNN-T inference without compromising model accuracy. During model infe…
HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR
Hainan Xu, Travis M. Bartley, Vladimir Bataev +1
We present Hybrid-Autoregressive INference TrANsducers (HAINAN), a novel architecture for speech recognition that extends the Token-and-Duration Transducer (TDT) model. Trained wit…
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
Daniel Galvez, Vladimir Bataev, Hainan Xu +1
The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of…