Story
Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU acceleration
1 report
1 website
1 discussion
Latest report
Overview
Frikallo/parakeet.cpp provides an ultra-fast and portable implementation of NVIDIA's Parakeet models for on-device speech recognition in C++. It achieves approximately 27ms encoder inference on Apple Silicon GPUs for 10 seconds of audio, making it 96 times faster than CPU processing, and utilizes the Axiom tensor library for automatic Metal GPU acceleration without heavy dependencies.
Summary from github.com.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · github.com
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-02-27.
- Praise: The ability to run multiple model families for various tasks like offline transcription and speaker diarization showcases the versatility of the Parakeet ASR engine, which is crucial for diverse applications.
- Praise: Local inference capabilities in C++ are becoming more accessible, enabling developers to create efficient pipelines for new models quickly, which can significantly enhance the development of speech recognition technologies.
- Praise: Users report being impressed with the performance of Parakeet on both Windows and Mac, indicating its reliability and effectiveness across platforms.
- Concern: Concerns about achieving low latency under 100ms for speech recognition persist, which is critical for real-time applications and user experience.
- Concern: Some users suggest that using CoreML with the Apple Neural Engine may provide better speed and power efficiency compared to Metal, raising questions about the optimal platform for ASR inference.