Olive: Simplify ML Model Finetuning, Conversion, Quantization, and Optimization for CPUs, GPUs and NPUs.

A curated list of awesome voice conversion, projects and communities.

Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

Remote heart rate detection through Eulerian magnification of face videos

Desktop implementation of Remote Photoplethysmography – Measuring heart rate using facial video.

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Like cURL, but for gRPC: Command-line tool for interacting with gRPC servers

Speech-to-text, text-to-speech, speaker diarization, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC…

Port of Funasr's Sense-voice model in C/C++

利用语言模型，纠正OCR识别错误

papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face D…

Paper collection of about the face anti-spoofing

Clone of the mercurial repository http://zbar.hg.sourceforge.net:8000/hgroot/zbar/zbar

👁️ 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI and more...

①[ICLR2024 Spotlight] (GPT-4V/Gemini-Pro/Qwen-VL-Plus+16 OS MLLMs) A benchmark for multi-modality LLMs (MLLMs) on low-level vision and visual quality assessment.

DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer (CVPR 2024)

A comprehensive collection of IQA papers

寧波話吳語拼音輸入方案 · 宁波话吴语拼音输入方案 · A Rime input schema for Ningbo Dialect

甬江話字詞表・A dictionary for Ningbo Dialect

Multilingual Voice Understanding Model

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

FaceChain is a deep-learning toolchain for generating your Digital-Twin.

UT-Sarulab MOS prediction system using SSL models

Application of MB-iSTFT-VITS components to vits2_pytorch

Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform