# Moonshine: Speech Recognition for Live Transcription and Voice Commands

arXiv: https://arxiv.org/abs/2410.15608 · HTML: https://mlsanity.com/paper/2410.15608/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 15 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [SOAP: Improving and Stabilizing Shampoo using Adam](https://mlsanity.com/paper/2409.11321/) (2024)
- [The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage](https://mlsanity.com/paper/2111.09344/) (2021)

## Built on by (most cited first, 19 of 19)

- [Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation](https://mlsanity.com/paper/2510.06961/) (2025)
- [LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation](https://mlsanity.com/paper/2502.20583/) (2025)
- [Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models](https://mlsanity.com/paper/2507.07877/) (2025)
- [On the Robust Approximation of ASR Metrics](https://mlsanity.com/paper/2502.12408/) (2025)
- [Flavors of Moonshine: Tiny Specialized ASR Models for Edge Devices](https://mlsanity.com/paper/2509.02523/) (2025)
- [Pushing the Limits of On-Device Streaming ASR: A Compact, High-Accuracy English Model for Low-Latency Inference](https://mlsanity.com/paper/2604.14493/) (2026)
- [Benchmarking Rotary Position Embeddings for Automatic Speech Recognition](https://mlsanity.com/paper/2501.06051/) (2025)
- [Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA](https://mlsanity.com/paper/2503.05840/) (2025)
- [BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encoder](https://mlsanity.com/paper/2606.22824/) (2026)
- [Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations](https://mlsanity.com/paper/2505.05056/) (2025)
- [Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models](https://mlsanity.com/paper/2601.02455/) (2026)
- [VibeVoice-ASR-BitNet Technical Report](https://mlsanity.com/paper/2607.21075/) (2026)
- [Towards Quantifying Benchmark Optimization in ASR Models](https://mlsanity.com/paper/2608.19936/) (2026)
- [MedWER: A Reproducible, Model-Free Evaluation Protocol for Medical Speech Recognition](https://mlsanity.com/paper/2609.05728/) (2026)
- [BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization](https://mlsanity.com/paper/2609.29069/) (2026)
- [Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognition](https://mlsanity.com/paper/2609.35564/) (2026)
- [FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs](https://mlsanity.com/paper/2609.38897/) (2026)
- [O'ido: Open-Vocabulary Speech Recognition on a 5 Microcontroller without a Neural Accelerator](https://mlsanity.com/paper/2610.13447/) (2026)
- [CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition](https://mlsanity.com/paper/2610.19134/) (2026)

## 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.