mlsanityData to 7 Oct 2026

Moonshine: Speech Recognition for Live Transcription and Voice Commands

arXiv 2410.15608 ↗First posted 21 Oct 2024cs.SD cs.CL cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 10 of its 15 references that are in the map. First posted on arXiv 21 Oct 2024.

Builds on

10 of 15 references.

References · 10

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  6. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 467
  7. 2021GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audiocited by 391
  8. 2023WhisperX: Time-Accurate Speech Transcription of Long-Form Audiocited by 320
  9. 2024SOAP: Improving and Stabilizing Shampoo using Adamcited by 179
  10. 2021The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usagecited by 98

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 9.

17 papers.

Sort:

  1. 2025Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluationcited by 21
  2. 2025LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximationcited by 7
  3. 2025Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Modelscited by 5
  4. 2025On the Robust Approximation of ASR Metricscited by 2
  5. 2026Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inferencecited by 2
  6. 2025Benchmarking Rotary Position Embeddings for Automatic Speech Recognitioncited by 1
  7. 2025Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHAcited by 1
  8. 2025Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devicescited by 1
  9. 2026BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encodercited by 1
  10. 2025Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotationscited by 0
  11. 2026Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Modelscited by 0
  12. 2026VibeVoice-ASR-BitNet Technical Reportcited by 0
5 more
  1. 2026Towards Quantifying Benchmark Optimization in ASR Modelscited by 0
  2. 2026MedWER: A Reproducible, Model-Free Evaluation Protocol for Medical Speech Recognitioncited by 0
  3. 2026BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularizationcited by 0
  4. 2026Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognitioncited by 0
  5. 2026FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRscited by 0