Papers
arxiv:2611.20064

Decode Early, Verify Late: Streaming Offline Speech Recognizers Without Accuracy Loss

Published on Nov 15
Authors:

Abstract

Voice agents need accurate transcripts soon after a user stops speaking. We propose Decode Early, Verify Late (DEVL), a training-free framework for streaming inference with offline ASR models. The server keeps partial transcripts as drafts and verifies the latest against the complete audio in one forward pass at turn end. Under stated input and decoding conditions, the final equals the model's greedy offline output in exact arithmetic. We adapt DEVL to four model families. In our five-recognizer comparison, 95-100% of final transcripts are byte-identical to the offline transcripts, WER stays within 0.13 points of offline, and single-stream time to final falls 1.5-7.3x. Serving Qwen3-ASR-1.7B on one A100, DEVL returns finals a median 22-26 ms after turn end at up to 64 streams, 2.7-3.9x sooner than the official streaming mode. It is the only system we tested that meets a 100 ms p99 target, up to 80 streams on Pipecat-STT and 64 on WildASR.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.20064
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.20064 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.20064 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.20064 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.