SWIM scales Whisper ASR to 20 concurrent multilingual clients via buffer merging, achieving ~2.4s delay at 5 clients versus 3.4s for single-client baselines while preserving accuracy.
Speed vs. Accuracy: Designing an Optimal ASR System for Spon- taneous Non-Native Speech in a Real-Time Application,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sink or SWIM: Tackling Real-Time ASR at Scale
SWIM scales Whisper ASR to 20 concurrent multilingual clients via buffer merging, achieving ~2.4s delay at 5 clients versus 3.4s for single-client baselines while preserving accuracy.