Saved in:
Bibliographic Details
Main Authors: Nethil, Kumarmanas, Mishra, Vaibhav, Anandan, Kriti, Manohar, Kavya
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.01021
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908536745754624
author Nethil, Kumarmanas
Mishra, Vaibhav
Anandan, Kriti
Manohar, Kavya
author_facet Nethil, Kumarmanas
Mishra, Vaibhav
Anandan, Kriti
Manohar, Kavya
contents We propose an open-source framework for Command-style dictation that addresses the gap between resource-intensive Online systems and high-latency Batch processing. Our approach uses Voice Activity Detection (VAD) to segment audio and transcribes these segments in parallel using Whisper models, enabling efficient multiplexing across audios. Unlike proprietary systems like SuperWhisper, this framework is also compatible with most ASR architectures, including widely used CTC-based models. Our multiplexing technique maximizes compute utilization in real-world settings, as demonstrated by its deployment in around 15% of India's courtrooms. Evaluations on live data show consistent latency reduction as user concurrency increases, compared to sequential batch processing. The live demonstration will showcase our open-sourced implementation and allow attendees to interact with it in real-time.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01021
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Scalable Offline ASR for Command-Style Dictation in Courtrooms
Nethil, Kumarmanas
Mishra, Vaibhav
Anandan, Kriti
Manohar, Kavya
Audio and Speech Processing
Computation and Language
Sound
We propose an open-source framework for Command-style dictation that addresses the gap between resource-intensive Online systems and high-latency Batch processing. Our approach uses Voice Activity Detection (VAD) to segment audio and transcribes these segments in parallel using Whisper models, enabling efficient multiplexing across audios. Unlike proprietary systems like SuperWhisper, this framework is also compatible with most ASR architectures, including widely used CTC-based models. Our multiplexing technique maximizes compute utilization in real-world settings, as demonstrated by its deployment in around 15% of India's courtrooms. Evaluations on live data show consistent latency reduction as user concurrency increases, compared to sequential batch processing. The live demonstration will showcase our open-sourced implementation and allow attendees to interact with it in real-time.
title Scalable Offline ASR for Command-Style Dictation in Courtrooms
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2507.01021