A hybrid decoding scheme with a fast TDT draft decoder and selective transformer patches matches baseline word error rate while cutting decoder latency roughly threefold.
Efficient sequence transduction by jointly pre- dicting tokens and durations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hybrid Decoding: Rapid Pass and Selective Detailed Correction for Sequence Models
A hybrid decoding scheme with a fast TDT draft decoder and selective transformer patches matches baseline word error rate while cutting decoder latency roughly threefold.