支持60种语言的纯JavaScript OCR
“> 将一张英文图片拖放到此页面上进行OCR识别!这看起来很棒,我真的很想试一试,但 > 未捕获的引用错误:progress 未定义 编辑:现在可以了!”
本地大模型运行时、AI 编程助手、推理引擎与前沿 RAG 架构。
支持60种语言的纯JavaScript OCR
“> 将一张英文图片拖放到此页面上进行OCR识别!这看起来很棒,我真的很想试一试,但 > 未捕获的引用错误:progress 未定义 编辑:现在可以了!”
using machine learning and computer vision
Automatic Speech Recognition in TensorFlow
Text-to-speech and speech-to-text open-source software stack
Set of trained deep learning models for computer vision
enhancing physical chessboards with computer vision
An On-Premises, Streaming Speech Recognition System
How we built a TTS-powered tool for learning spelling/foreign languages
Bounding-box labeler tool to generate the training data for YOLO v2
Live coaching app for remote SWE interviews, uses Whisper and GPT-4
State-of-the-art German speech recognition in 284 lines of C++
I made a free transcription service powered by Whisper AI