Moonshine: Speech Recognition for Live Transcription and Voice Commands

This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. Th...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-10
Main Authors: Jeffries, Nat, King, Evan, Manjunath Kudlur, Nicholson, Guy, Wang, James, Warden, Pete
Format: Article
Language:English
Subjects:
Encoders-Decoders
Error reduction
Real time
Segments
Speech recognition
Voice recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Jeffries, Nat
King, Evan
Manjunath Kudlur
Nicholson, Guy
Wang, James
Warden, Pete
description This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. The model is trained on speech segments of various lengths, but without using zero-padding, leading to greater efficiency for the encoder during inference time. When benchmarked against OpenAI's Whisper tiny-en, Moonshine Tiny demonstrates a 5x reduction in compute requirements for transcribing a 10-second speech segment while incurring no increase in word error rates across standard evaluation datasets. These results highlight Moonshine's potential for real-time and resource-constrained applications.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3119818109</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3119818109</sourcerecordid><originalsourceid>FETCH-proquest_journals_31198181093</originalsourceid><addsrcrecordid>eNqNis0KgkAURocgSMp3GGgtzE-WtpV-FrUpaSsyXXMk77UZ7fmT6AFafZxzvgkLlNYySlZKzVjofSOEUOuNimMdsMOZCH1tEbb82gGYml_A0ANtbwl5RY6f7Bt47kr0xtnuq0u88xtZAzyjth3JL9i0Kp8ewt_O2XK_y7Nj1Dl6DeD7oqHB4ZgKLWWayESKVP_3-gDwXTuD</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3119818109</pqid></control><display><type>article</type><title>Moonshine: Speech Recognition for Live Transcription and Voice Commands</title><source>Publicly Available Content (ProQuest)</source><creator>Jeffries, Nat ; King, Evan ; Manjunath Kudlur ; Nicholson, Guy ; Wang, James ; Warden, Pete</creator><creatorcontrib>Jeffries, Nat ; King, Evan ; Manjunath Kudlur ; Nicholson, Guy ; Wang, James ; Warden, Pete</creatorcontrib><description>This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. The model is trained on speech segments of various lengths, but without using zero-padding, leading to greater efficiency for the encoder during inference time. When benchmarked against OpenAI's Whisper tiny-en, Moonshine Tiny demonstrates a 5x reduction in compute requirements for transcribing a 10-second speech segment while incurring no increase in word error rates across standard evaluation datasets. These results highlight Moonshine's potential for real-time and resource-constrained applications.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Encoders-Decoders ; Error reduction ; Real time ; Segments ; Speech recognition ; Voice recognition</subject><ispartof>arXiv.org, 2024-10</ispartof><rights>2024. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/3119818109?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Jeffries, Nat</creatorcontrib><creatorcontrib>King, Evan</creatorcontrib><creatorcontrib>Manjunath Kudlur</creatorcontrib><creatorcontrib>Nicholson, Guy</creatorcontrib><creatorcontrib>Wang, James</creatorcontrib><creatorcontrib>Warden, Pete</creatorcontrib><title>Moonshine: Speech Recognition for Live Transcription and Voice Commands</title><title>arXiv.org</title><description>This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. The model is trained on speech segments of various lengths, but without using zero-padding, leading to greater efficiency for the encoder during inference time. When benchmarked against OpenAI's Whisper tiny-en, Moonshine Tiny demonstrates a 5x reduction in compute requirements for transcribing a 10-second speech segment while incurring no increase in word error rates across standard evaluation datasets. These results highlight Moonshine's potential for real-time and resource-constrained applications.</description><subject>Encoders-Decoders</subject><subject>Error reduction</subject><subject>Real time</subject><subject>Segments</subject><subject>Speech recognition</subject><subject>Voice recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNis0KgkAURocgSMp3GGgtzE-WtpV-FrUpaSsyXXMk77UZ7fmT6AFafZxzvgkLlNYySlZKzVjofSOEUOuNimMdsMOZCH1tEbb82gGYml_A0ANtbwl5RY6f7Bt47kr0xtnuq0u88xtZAzyjth3JL9i0Kp8ewt_O2XK_y7Nj1Dl6DeD7oqHB4ZgKLWWayESKVP_3-gDwXTuD</recordid><startdate>20241022</startdate><enddate>20241022</enddate><creator>Jeffries, Nat</creator><creator>King, Evan</creator><creator>Manjunath Kudlur</creator><creator>Nicholson, Guy</creator><creator>Wang, James</creator><creator>Warden, Pete</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20241022</creationdate><title>Moonshine: Speech Recognition for Live Transcription and Voice Commands</title><author>Jeffries, Nat ; King, Evan ; Manjunath Kudlur ; Nicholson, Guy ; Wang, James ; Warden, Pete</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31198181093</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Encoders-Decoders</topic><topic>Error reduction</topic><topic>Real time</topic><topic>Segments</topic><topic>Speech recognition</topic><topic>Voice recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Jeffries, Nat</creatorcontrib><creatorcontrib>King, Evan</creatorcontrib><creatorcontrib>Manjunath Kudlur</creatorcontrib><creatorcontrib>Nicholson, Guy</creatorcontrib><creatorcontrib>Wang, James</creatorcontrib><creatorcontrib>Warden, Pete</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Jeffries, Nat</au><au>King, Evan</au><au>Manjunath Kudlur</au><au>Nicholson, Guy</au><au>Wang, James</au><au>Warden, Pete</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Moonshine: Speech Recognition for Live Transcription and Voice Commands</atitle><jtitle>arXiv.org</jtitle><date>2024-10-22</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>This paper introduces Moonshine, a family of speech recognition models optimized for live transcription and voice command processing. Moonshine is based on an encoder-decoder transformer architecture and employs Rotary Position Embedding (RoPE) instead of traditional absolute position embeddings. The model is trained on speech segments of various lengths, but without using zero-padding, leading to greater efficiency for the encoder during inference time. When benchmarked against OpenAI's Whisper tiny-en, Moonshine Tiny demonstrates a 5x reduction in compute requirements for transcribing a 10-second speech segment while incurring no increase in word error rates across standard evaluation datasets. These results highlight Moonshine's potential for real-time and resource-constrained applications.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_3119818109
source Publicly Available Content (ProQuest)
subjects Encoders-Decoders
Error reduction
Real time
Segments
Speech recognition
Voice recognition
title Moonshine: Speech Recognition for Live Transcription and Voice Commands
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-21T04%3A23%3A29IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Moonshine:%20Speech%20Recognition%20for%20Live%20Transcription%20and%20Voice%20Commands&rft.jtitle=arXiv.org&rft.au=Jeffries,%20Nat&rft.date=2024-10-22&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E3119818109%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31198181093%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3119818109&rft_id=info:pmid/&rfr_iscdi=true