MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

On-device Speech Recognition for Apple Silicon

TheBoringNotch: Not so boring notch That Rocks 🎸🎶

The smartest way to learn touch typing and improve your typing speed.

Simple image captioning model

CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)

Schedule-Free Optimization in PyTorch

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

PyTorch implementation of the InfoNCE loss for self-supervised learning.

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

[ICLR'23] AIM: Adapting Image Models for Efficient Video Action Recognition

Django Channels based WebSocket GraphQL server with Graphene-like subscriptions

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Framework for benchmarking fully-managed vector databases

Perceptual video quality assessment based on multi-method fusion.

Highly commented implementations of Transformers in PyTorch

Applying the latest advancements in AI and machine learning to solve complex business problems.

a state-of-the-art-level open visual language model | 多模态预训练模型

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Incredibly descriptive audiovisual summaries for videos

tiny vision language model

Automatically optimize SQL queries in Graphene-Django schemas.

A family of lightweight multimodal models.

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

Learning audio concepts from natural language supervision

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

VideoCC is a dataset containing (video-URL, caption) pairs for training video-text machine learning models. It is created using an automatic pipeline starting from the Conceptual Captions Image-Cap…

A language for constraint-guided and efficient LLM programming.