Search Results for "high compression ratio"
Sort By:
Showing 27 open source projects for "high compression ratio"
View related business solutions-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
1
Wan2.2
Wan2.2: Open and Advanced Large-Scale Video Generative Model
...It introduces a Mixture-of-Experts (MoE) architecture that splits the denoising process across specialized expert models, increasing total model capacity without raising computational costs. Wan2.2 integrates meticulously curated cinematic aesthetic data, enabling precise control over lighting, composition, color tone, and more, for high-quality, customizable video styles. The model is trained on significantly larger datasets than its predecessor, greatly enhancing motion complexity, semantic understanding, and aesthetic diversity. Wan2.2 also open-sources a 5-billion parameter high-compression VAE-based hybrid text-image-to-video (TI2V) model that supports 720P video generation at 24fps on consumer-grade GPUs like the RTX 4090. ... -
2
FramePack
Lets make video diffusion practical
FramePack explores compact representations for sequences of image frames, targeting tasks where many near-duplicate frames carry redundant information. The idea is to “pack” frames by detecting shared structure and storing differences efficiently, which can accelerate training or inference on video-like data. By reducing I/O and memory bandwidth, datasets become lighter to load while models still see the essential temporal variation. The repository demonstrates both packing and unpacking... -
3
DeepSpeed
Deep learning optimization library: makes distributed training easy
...Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme compression for an unparalleled inference latency and model size reduction with low costs DeepSpeed offers a confluence of system innovations, that has made large scale DL training effective, and efficient, greatly improved ease of use, and redefined the DL training landscape in terms of scale that is possible. ... -
4
Audiogen Codec
48khz stereo neural audio codec for general audio
AGC (Audiogen Codec) is a convolutional autoencoder based on the DAC architecture, which holds SOTA. We found that training with EMA and adding a perceptual loss term with CLAP features improved performance. These codecs, being low compression, outperform Meta's EnCodec and DAC on general audio as validated from internal blind ELO games. We trained (relatively) very low compression codecs in the pursuit of solving a core issue regarding general music and audio generation, low acoustic quality, and audible artifacts, which hinder industry use for these models. Our hope is to encourage researchers to build hierarchical generative audio models that can efficiently use high sequence length representations without sacrificing semantic abilities. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
FlexLLMGen
Running large language models on a single GPU
FlexLLMGen is an open-source inference engine designed to run large language models efficiently on limited hardware resources such as a single GPU. The system focuses on high-throughput generation workloads where large batches of text must be processed quickly, such as large-scale data extraction or document analysis tasks. Instead of requiring expensive multi-GPU systems, the framework uses techniques such as memory offloading, compression, and optimized batching to run large models on commodity hardware. ... -
6
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle
...Inspired by PaddlePaddle, PaddleOCR is an ultra lightweight OCR system, with multilingual recognition, digit recognition, vertical text recognition, as well as long text recognition. It features a PPOCR series of high-quality pre-trained models, which includes: ultra lightweight ppocr_mobile series models, general ppocr_server series models, and ultra lightweight compression ppocr_mobile_slim series models. PaddleOCR is easy to install and easy to use on Windows, Linux, MacOS and other systems. -
7
WavTokenizer
SOTA discrete acoustic codec models with 40/75 tokens per second
WavTokenizer is a state-of-the-art discrete acoustic codec designed specifically for audio language modeling, capable of compressing 24 kHz audio into just 40 or 75 tokens per second while preserving high perceptual quality. It is built to represent speech, music, and general audio with extremely low bitrate, making it ideal as a front-end for large audio language models like GPT-4o and similar architectures. The model uses a single-quantizer design together with temporal compression to achieve extreme compression without sacrificing reconstruction fidelity. ... -
8
Django MarkdownX
Comprehensive Markdown plugin built for Django
Django MarkdownX is a comprehensive Markdown plugin built for Django, the renowned high-level Python web framework, with flexibility, extensibility, and ease-of-use at its core. -
9
AWS SDK for pandas
Easy integration with Athena, Glue, Redshift, Timestream, Neptune
aws-sdk-pandas (formerly AWS Data Wrangler) bridges pandas with the AWS analytics stack so DataFrames flow seamlessly to and from cloud services. With a few lines of code, you can read from and write to Amazon S3 in Parquet/CSV/JSON/ORC, register tables in the AWS Glue Data Catalog, and query with Amazon Athena directly into pandas. The library abstracts efficient patterns like partitioning, compression, and vectorized I/O so you get performant data lake operations without hand-rolling... -
Add Two Lines of Code. Get Full APM.Works out of the box for Rails, Django, Express, Phoenix, and more. Monitoring exceptions and performance in no time.
-
10
ERNIE
The official repository for ERNIE 4.5 and ERNIEKit
ERNIE is an open-source large-model toolkit and model family from the PaddlePaddle ecosystem that focuses on training, fine-tuning, compression, and practical application of ERNIE large language models. The repository positions ERNIEKit as an industrial-grade development toolkit, emphasizing end-to-end workflows that span high-performance pre-training, supervised fine-tuning, and alignment. It supports both full-parameter training and parameter-efficient approaches so teams can choose between maximum quality and lower-cost adaptation depending on their constraints. ... -
11
AV1 AVIF
AV1 Image File Format Specification - ISO-BMFF/HEIF derivative
AV1 AVIF is the official specification and reference design for the AV1 Image File Format (AVIF), defining how AV1-encoded bitstreams are packaged into the HEIF container format (based on ISOBMFF) to produce AVIF files. The project outlines the syntax and semantics required for AVIF compliance, including support for multiple image profiles, color depths, chroma subsampling modes, HDR/WCG, alpha channels, animation/image sequences, and various color-space/bit-depth combinations — making AVIF... -
12
DLRM
An implementation of a deep learning recommendation model (DLRM)
...It includes data loaders for standard benchmarks (like Criteo), training scripts, evaluation tools, and capabilities like mixed precision, gradient compression, and memory fusion to maximize throughput. -
13
AWS IoT Device SDK v2 for Python
Next generation AWS IoT Client SDK for Python
...This document provides information about the AWS IoT Device SDK v2 for Python. This SDK is built on the AWS Common Runtime, a collection of libraries (aws-c-common, aws-c-io, aws-c-mqtt, aws-c-compression, aws-c-http, aws-c-cal, aws-c-auth, s2n ...) written in C to be cross-platform, high-performance, secure, and reliable. The libraries are bound to Python by the awscrt package (PyPI). AWS IoT provides the cloud services that connect your IoT devices to other devices and AWS cloud services. AWS IoT provides device software that can help you integrate your IoT devices into AWS IoT-based solutions. ... -
14
OAGI Python SDK
Python SDK for the Computer Use model Lux, developed by OpenAGI
OAGI Python SDK is a Python client library for the Lux computer-use model that turns Lux into a programmable automation layer for operating human-facing software via vision and actions. It exposes the OAGI API in an ergonomic way, letting you trigger Lux in three main modes: Tasker for precise scripted sequences, Actor for fast one-shot tasks, and Thinker for open-ended, multi-step objectives. The SDK is designed around “computer use” as a paradigm, where the AI actually navigates... -
15
Arctic TimeSeries and Tick store
High performance datastore for time series and tick data
Arctic is a timeseries/dataframe database that sits atop MongoDB. Arctic supports serialization of a number of datatypes for storage in the mongo document model. Serializes a number of data types eg. Pandas DataFrames, Numpy arrays, Python objects via pickling etc. so you don't have to handle different datatypes manually. Uses LZ4 compression by default on the client side to get big savings on network / disk. Allows you to version different stages of an object and snapshot the state (In some... -
16
PI-Based Image Encoder / Converter
Python code able to convert / compress image to PI (3.14, π) Indexes
Image processing tool that encodes pixel data as indices within the first 16.7 million digits of PI (π). Features high-performance Numba-accelerated search and a signature 'film-grain' aesthetic upon reconstruction. ZIP also include 16 MB file with 16,7 mil numbers of PI Benchmark(Single-Thread): Hardware & Environment Apple Silicon: Apple M2 (Mac mini/MacBook) x86_64 Platform: Intel Core Ultra 5 225F (Arrow Lake, 10 Cores) OS 1: Fedora 43 (GNOME) OS 2: Windows 11 Pro... -
17
Qvid
Stream low latency video from your desktop or webcam over TCP/IP
Qvid is a demo video streaming application for Windows (MacOs support limited and currently broken), written in Python. It allows you to capture screenshots of your desktop, webcam, and selected windows programs. The captured images are compressed and sent as a continuous stream over a TCP connection to a single machine. Developed alongside https://sourceforge.net/projects/netjoy/ to allow for off-site, single and multiplayer, game play over an internet connection. -
18
crypto scanner v6.0.0
AI‑powered signals, risk analysis, and automated trading bot
Advanced Crypto Scanner v6.0.0 All‑in‑one Windows crypto tool – real‑time data, signals, risk analysis, AI learning, and automated trading bot. Live Data: Prices, volume, market cap (CoinMarketCap/CoinGecko), BTC dominance, market sentiment. Smart Signals: Basic (price/volume) & Advanced (RSI, MACD, Bollinger, Stochastic, ADX) with confirmation gate. Risk Rating: Low/Medium/High based on liquidity, volatility, category, technicals. Filters: Category (DeFi, AI, Gaming, NFT, Meme,... -
19
CLIP-as-service
Embed images and sentences into fixed-length vectors
...No learning curve, minimalist design on client and server. Intuitive and consistent API for image and sentence embedding. Async client support. Easily switch between gRPC, HTTP, WebSocket protocols with TLS and compression. Smooth integration with neural search ecosystem including Jina and DocArray. Build cross-modal and multi-modal solutions in no time. -
20
Sweetviz
Visualize and compare datasets, target values and associations
Sweetviz is an open-source Python library that generates beautiful, high-density visualizations to kickstart EDA (Exploratory Data Analysis) with just two lines of code. Output is a fully self-contained HTML application. The system is built around quickly visualizing target values and comparing datasets. Its goal is to help quick analysis of target characteristics, training vs testing data, and other such data characterization tasks. -
21
LAME (Lame Aint an MP3 Encoder)
A high quality MP3 encoder
LAME is an educational tool to be used for learning about MP3 encoding. The goal of the LAME project is to improve the psycho acoustics, quality and speed of MP3 encoding. Note: we provide source code only! -
22
Bulk Image Optimizer and Converter
Imagine having all your images well compressed and optimized :)
...The optimized images are saved in a separate folder named "optimized" within the input folder. The tool displays progress information, including the number of images processed, the average compression ratio, and the total space saved. -
23
EnCodec
State-of-the-art deep learning based audio codec
Encodec is a neural audio codec developed by Meta for high-fidelity, low-bitrate audio compression using end-to-end deep learning. Unlike traditional codecs (like MP3 or Opus), Encodec uses a learned quantizer and decoder to reconstruct complex waveforms with remarkable accuracy at bitrates as low as 1.5 kbps. It employs a convolutional encoder–decoder architecture trained with perceptual loss functions that optimize for human auditory quality rather than raw waveform distance. ... -
24
MAE (Masked Autoencoders)
PyTorch implementation of MAE
MAE (Masked Autoencoders) is a self-supervised learning framework for visual representation learning using masked image modeling. It trains a Vision Transformer (ViT) by randomly masking a high percentage of image patches (typically 75%) and reconstructing the missing content from the remaining visible patches. This forces the model to learn semantic structure and global context without supervision. The encoder processes only the visible patches, while a lightweight decoder reconstructs the... -
25
Minkowski Engine
Auto-diff neural network library for high-dimensional sparse tensors
The Minkowski Engine is an auto-differentiation library for sparse tensors. It supports all standard neural network layers such as convolution, pooling, unspooling, and broadcasting operations for sparse tensors. The Minkowski Engine supports various functions that can be built on a sparse tensor. We list a few popular network architectures and applications here. To run the examples, please install the package and run the command in the package root directory. Compressing a neural network to...
