1.datalab-to / indra
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
+491 stars
from 1,086 · score 6.20
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
21 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.k2-fsa / sherpa-onnx
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
+155 stars
from 15,510 · score 5.05
3.dsmurrell / onkey
Learn to sing the songs you love. A free, open-source singing trainer for Mac that listens to the music you play.
+81 stars
from 306 · score 4.41
4.niedev / RTranslator
Open source real-time translation app for Android that runs locally
+54 stars
from 10,548 · score 4.01
5.tracel-ai / burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
+47 stars
from 16,161 · score 3.87
6.langchain4j / langchain4j
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
+43 stars
from 13,295 · score 3.78
7.microsoft / onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
+38 stars
from 22,172 · score 3.66
8.lutzroeder / netron
Visualizer for neural network, deep learning and machine learning models
+29 stars
from 33,611 · score 3.40
9.ultralytics / yolov5
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
+26 stars
from 58,221 · score 3.30
10.Tencent / ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
+20 stars
from 23,997 · score 3.04
11.onnx / onnx
Open standard for machine learning interoperability
+17 stars
from 21,617 · score 2.89
12.0c-biggo / 0c-ime
免選字的注音輸入法：在本機用 Transformer 看前文選字。支援 Linux（Fcitx5／IBus）、macOS、Windows。
+14 stars
from 143 · score 2.71
13.google / magika
Fast and accurate AI powered file content types detection
+13 stars
from 18,744 · score 2.64
14.Megvii-BaseDetection / YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
+9 stars
from 10,675 · score 2.30
15.ultralytics / yolov3
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
+7 stars
from 10,624 · score 2.08
16.microsoft / SynapseML
Simple and Distributed Machine Learning Python Library porting ML algorithms for Spark
+3 stars
from 5,249 · score 1.39
17.hybridgroup / gocv
Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.
+2 stars
from 7,516 · score 1.10
18.llmware-ai / llmware
Unified framework for building enterprise RAG pipelines with small, specialized models
+1 stars
from 14,817 · score 0.69
19.microsoft / MMdnn
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
+1 stars
from 5,803 · score 0.69
20.oramasearch / onnx-go
onnx-go gives the ability to import a pre-trained neural network within Go without being linked to a framework or library.
+1 stars
from 908 · score 0.69
21.gmalivenko / pytorch2keras
PyTorch to Keras model convertor
+1 stars
from 860 · score 0.69