kroko-ai/kroko-onnx
Kroko ASR - Speech-to-text
Leverages ONNX Runtime for cross-platform deployment (native Android, WebAssembly in browsers, Linux/Docker servers) with streaming WebSocket endpoints that emit real-time partial and final transcriptions. Models are built on transducer architecture with configurable decoding methods (greedy search or modified beam search), endpoint detection, and optional GPU acceleration (CUDA, CoreML), supporting both open-source community models and commercial variants with license keys.
138 stars. No commits in the last 6 months.
Stars
138
Forks
10
Language
C++
License
Apache-2.0
Category
Last pushed
Oct 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kroko-ai/kroko-onnx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/PaddleSpeech
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with...
k2-fsa/sherpa
Speech-to-text server framework with next-gen Kaldi
Picovoice/cheetah
On-device streaming speech-to-text engine powered by deep learning
Picovoice/leopard
On-device speech-to-text engine powered by deep learning
zaigie/FunSpeech
开箱即用的本地私有化部署语音服务，快速搭建FunASR与CosyVoice2/3后端