Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/moonshine
Library/moonshineForked

moonshine-ai/moonshine

moonshine

Fast and accurate automatic speech recognition (ASR) for edge devices

View on GitHub↗Upstream moonshine-ai/moonshine↗

Builder

moonshine-ai

moonshine-ai

moonshine-ai • individual

Stars

8,299

Using upstream star count

Forks

439

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Oct 4, 2024

Project creation date

README Summary

- [Quickstart](#quickstart) - [When should you choose Moonshine over Whisper?](#when-should-you-choose-moonshine-over-whisper) - [Using the Library](#using-the-library) - [Models](#models) - [API Reference](#api-reference) - [Support](#support) - [Roadmap](#roadmap) - [Acknowledgements](#acknowledgements) - [License](#license)

Community Evaluation

Loading…

AI Dev Skills

Unmapped

Audio Feature ExtractionAutomatic Speech RecognitionEdge AI OptimizationEmbedded Machine LearningLow-latency InferenceModel QuantizationNeural Network CompressionReal-time Audio Processing

Tags

Audio Feature ExtractionAutomatic Speech RecognitionEdge AI OptimizationEmbedded Machine LearningLow-latency InferenceModel QuantizationNeural Network CompressionReal-time Audio ProcessingAPIBenchmarkingC++CachingCourseEmbeddingsEvalsForkedHuggingFaceInferenceMobileModel OptimizationONNXOpen SourceOpenAIPlanning / CoTPythonQuantizationReal-Time / StreamingResearch / PapersRoadmapSpeech to TextTransformersTutorial

Taxonomy

AI Trends

On-device AIEdge ComputingModel CompressionReal-time AI

category

Learning ResourcesFoundation ModelsAI AgentsRAG & RetrievalEvals & BenchmarkingInference & ServingGenerative MediaDev Tools & Automation

Deployment Context

Edge/MobileEmbedded SystemsOn-device

Industries

Mobile TechnologyIoTAutomotiveHealthcareSmart HomeRoboticsAccessibility Technology

Modalities

Audio

Skill Areas

Automatic Speech RecognitionEdge AI OptimizationReal-time Audio ProcessingModel QuantizationLow-latency InferenceEmbedded Machine LearningAudio Feature ExtractionNeural Network Compression

tag

APIBenchmarkingC++CachingCourseEmbeddingsEvalsForkedHuggingFaceInferenceMobileModel OptimizationONNXOpen SourceOpenAIPlanning / CoTPythonQuantizationReal-Time / StreamingResearch / PapersRoadmapSpeech to TextTransformersTutorial

Use Cases

Real-time Voice TranscriptionVoice Command ProcessingOffline Speech RecognitionVoice-controlled ApplicationsSpeech-to-text for Mobile AppsEdge Voice Assistants

Recent Activity

Updated 2 months ago

7 Days

0

30 Days

0

90 Days

1

Fixed crash when transcription is disabled

Pete Warden • Mar 10, 2026

e7f4e48

Example of calling Ollama models with a voice interface

Pete Warden • Mar 3, 2026

7c2c1c4

Prevent double-firing of line completion event on Android

Pete Warden • Feb 28, 2026

79b0217

Quality

beta
Quality
medium
Maturity
beta

Categories

Learning ResourcesPrimaryRAG & RetrievalEvals & BenchmarkingInference & ServingDev Tools & AutomationFoundation ModelsAI AgentsGenerative MediaEdge & Mobile AISearch & KnowledgeOther AI / ML

PM Skills

Cost & EfficiencyUser ExperienceScale & ReliabilityData & EvaluationProduct DiscoveryDeveloper PlatformAI-Native Architecture

Languages

C100.0%

Timeline

Project created
Oct 4, 2024
Forked
Mar 12, 2026
Your last push
2 months ago
Upstream last push
18 days ago
Tracked since
Mar 10, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…