Search Results for "encoder"
Sort By:
Showing 270 open source projects for "encoder"
View related business solutions-
Go beyond a virtual data room with Datasite DiligenceThe data room with a view. Evolved for next-generation M&A. Built on decades of deal experience. Packed with expert tools, yet intuitive for novices. A fully mobile platform with frictionless processes. Smart AI tools that let you close more deals, faster, plus end-to-end support at all times. Do due diligence with intelligence.
-
Caller ID Reputation provides the most comprehensive view of your caller ID scores across all carriersKeep your agents on the phone with increased connection rates by monitoring your phone number reputation across all major carriers and call blocking apps.
-
1
Logstash Logback Encoder
Logback JSON encoder and appenders
Provides log back encoders, layouts, and appenders to log in JSON and other formats supported by Jackson. Supports both regular LoggingEvents (logged through a Logger) and AccessEvents (logged via logback-access). Originally written to support output in Logstash's JSON format, but has evolved into a highly configurable, general-purpose, structured logging mechanism for JSON and other Jackson data forms. The structure of the output, and the data it contains, is fully configurable. The general... -
2
Pytorch-toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming
...Extras for Catalyst library (Visualization of batch predictions, additional metrics). By design, both encoder and decoder produces a list of tensors, from fine (high-resolution, indexed 0) to coarse (low-resolution) feature maps. Access to all intermediate feature maps is beneficial if you want to apply deep supervision losses on them or encoder-decoder of object detection task. -
3
simplejson
simplejson is a simple, fast, extensible JSON encoder/decoder
...The encoder can be specialized to provide serialization in any kind of situation, without any special support by the objects to be serialized (somewhat like pickle). This is best done with the default kwarg to dumps. -
4
rav1e
The fastest and safest AV1 encoder
rav1e is an open-source implementation of an encoder for the AV1 video codec, developed in Rust (with some assembly) by the community around Xiph Foundation. Its design philosophy is to start from a correct, minimal, and fast AV1 encoder — sacrificing some encoding speed/efficiency of reference encoders in exchange for simplicity, stability, and compilability across platforms — and then gradually improve. -
DataHub is the leading open-source data catalog helping teams discover, understand, and govern their data assets.Built on an open source foundation with a thriving community of 13,000+ members, DataHub gives you unmatched flexibility to customize and extend without vendor lock-in. DataHub Cloud is a modern metadata platform with REST and GraphQL APIs that optimize performance for complex queries, essential for AI-ready data management and ML lifecycle support.
-
5
ModernBERT
Bringing BERT into modernity via both architecture changes and scaling
ModernBERT is an open-source research project that modernizes the classic BERT encoder architecture by incorporating recent advances in transformer design, training techniques, and efficiency improvements. The goal of the project is to bring BERT-style models up to date with the capabilities of modern large language models while preserving the strengths of bidirectional encoder architectures used for tasks such as classification, retrieval, and semantic search. -
6
Shutter Encoder
Free professional video converter Windows|Mac|Linux
Shutter Encoder is an video, audio and image converter based on FFmpeg and other great tools. It has been designed by video editors in order to be as accessible and efficient as possible. It's a swiss knife tool for any video editor. Link to website & downloads : https://www.shutterencoder.com - Without conversion: Cut without re-encoding, Replace audio, Rewrap, Conform, Merge, Extract, Subtitling, Video inserts - Sound conversions: WAV, AIFF, FLAC, ALAC, MP3, AAC, AC3, OPUS, OGG - Editing codecs: DNxHD, DNxHR, Apple ProRes, QT Animation, GoPro CineForm, Uncompressed YUV - Output codecs: H.264, H.265, VP8, VP9, AV1, OGV - Broadcast codecs: XDCAM HD422, AVC-Intra 100, XAVC, HAP - Old codecs: DV PAL, MJPEG, Xvid, WMV, MPEG - Archiving codec: FFV1 - Images creation: JPEG, Image - Burn & Rip: DVD, Blu-ray, DVD RIP - Analysis: Loudness & True Peak, Audio normalization, Cut detection, Black detection, Media, VMAF - Download: Web video -
7
rtmp-rtsp-stream-client-java
Library to stream in rtmp and rtsp for Android. All code in Java
Library for streaming in RTMP and RTSP. All code in Java. -
8
go-json
Fast JSON encoder/decoder compatible with encoding/json for Go
Fast JSON encoder/decoder compatible with encoding/json for Go. -
9
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. The design tackles long-standing conflicts in multimodal models: namely that the visual encoder has to serve both analysis (understanding) and synthesis (generation) roles. By splitting those pathways but keeping one unified core transformer, Janus maintains flexibility and achieves strong performance across tasks previously requiring distinct architectures. ... -
Automate Proposals with AI in Microsoft Word.Automate your best practices, processes, and standards to guide your proposal writers, sales teams, and subject experts. And don’t worry, it’s so easy to use they will use it. We would love the opportunity to help you quantify the impact your business can expect from investing in Expedience Software. Click here to request a Return on Investment (ROI) calculation. In this 15-minute session, we will ask 20 simple questions to assess and grade your current proposal quality and scalability. Manual proposal processes are likely costing you far more than you realize. These models waste time and kill the productivity of proposal writers, sales team members, senior staff, and subject experts.
-
10
FastVLM
This repository contains the official implementation of FastVLM
...The repository documents model variants, showcases head-to-head numbers against known baselines, and explains how the encoder integrates with common LLM backbones. Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
11
laravel-encoder
The Laravel Encoder package provides a robust and secure way to encode
The Laravel Encoder package provides a robust and secure way to encode and decode IDs & Strings using customizable Base encoding mechanisms (Base62). With support for variable-length encoding, mappers for added security, and seamless integration with Laravel, this package is ideal for obfuscating sensitive data or creating URL-safe identifiers. -
12
IndexTTS2
Industrial-level controllable zero-shot text-to-speech system
IndexTTS is a modern, zero-shot text-to-speech (TTS) system engineered to deliver high-quality, natural-sounding speech synthesis with few requirements and strong voice-cloning capabilities. It builds on state-of-the-art models such as XTTS and other modern neural TTS backbones, improving them with a conformer-based speech conditional encoder and upgrading the decoder to a high-quality vocoder (BigVGAN2), leading to clearer and more natural audio output. The system supports zero-shot voice cloning — meaning it can mimic a target speaker’s voice from a short reference sample — making it versatile for multi-voice uses. Compared to many open-source TTS tools, IndexTTS emphasizes efficiency and controllability: it offers faster inference, simpler training pipelines, and controllable speech parameters (like duration, pitch, and prosody), which is critical for production use. -
13
nghttp2
HTTP/2 C Library and tools
...Since then we have updated nghttp2 library constantly to the latest specification and nghttp2 is now one of the most mature HTTP/2 implementations. HTTP/2 utilizes header compression method called HPACK. We offer HPACK encoder and decoder are available as public API. nghttp2 library itself is a bit low-level. The experimental high-level C++ API is also available. We have Python binding of this library, but we have not covered everything yet. -
14
Memvid
Video-based AI memory library. Store millions of text chunks in MP4
Memvid encodes text chunks as QR codes within MP4 frames to build a portable “video memory” for AI systems. This innovative approach uses standard video containers and offers millisecond-level semantic search across large corpora with dramatically less storage than vector DBs. It's self-contained—no DB needed—and supports features like PDF indexing, chat integration, and cloud dashboards. -
15
MedGemma
Collection of Gemma 3 variants that are trained for performance
...It includes multiple variants such as a 4 billion-parameter multimodal model that can process both medical images and text and a 27 billion-parameter text-only (and multimodal) model that offers deeper clinical reasoning and understanding at higher capacity, making it suitable for complex tasks like medical question answering, summarization of clinical notes, or generating reports from radiology images. The multimodal versions pair a SigLIP-based image encoder pre-trained on diverse de-identified medical imaging data. -
16
Poison
An incredibly fast, pure Elixir JSON library
Poison is a fast and lightweight JSON library for Elixir focused on performance and idiomatic APIs. It provides straightforward encode and decode functions, along with a protocol-based encoder that lets you customize how your structs become JSON. Developers can derive or implement Poison.Encoder for domain types, control which fields are included, and map complex values into JSON-friendly forms. On the decoding side, it supports options for key handling and flexible parsing of JSON into Elixir maps, lists, and primitive values. ... -
17
Bootstrap Your Own Latent (BYOL)
Usable Implementation of "Bootstrap Your Own Latent" self-supervised
Practical implementation of an astoundingly simple method for self-supervised learning that achieves a new state-of-the-art (surpassing SimCLR) without contrastive learning and having to designate negative pairs. This repository offers a module that one can easily wrap any image-based neural network (residual network, discriminator, policy network) to immediately start benefitting from unlabelled image data. There is now new evidence that batch normalization is key to making this technique... -
18
ESPnet
End-to-end speech processing toolkit
...ESPnet provides many ready-to-run recipes for popular academic benchmarks, making it straightforward to reproduce published results or serve as baselines for new research. The toolkit also hosts numerous pretrained models and example configs, ranging from Transformer and Conformer architectures to various attention-based encoder-decoder models. -
19
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
JEPA (Joint-Embedding Predictive Architecture) captures the idea of predicting missing high-level representations rather than reconstructing pixels, aiming for robust, scalable self-supervised learning. A context encoder ingests visible regions and predicts target embeddings for masked regions produced by a separate target encoder, avoiding low-level reconstruction losses that can overfit to texture. This makes learning focus on semantics and structure, yielding features that transfer well with simple linear probes and minimal fine-tuning. The repository provides training recipes, data pipelines, and evaluation utilities for image JEPA variants and often includes ablations that illuminate which masking and architectural choices matter. ... -
20
MoCo (Momentum Contrast)
Self-supervised visual learning using momentum contrast in PyTorch
...It introduces Momentum Contrast (MoCo), a scalable approach to self-supervised learning that enables visual representation learning without labeled data. The core idea of MoCo is to maintain a dynamic dictionary with a momentum-updated encoder, allowing efficient contrastive learning across large batches. The repository includes implementations for both MoCo v1 and MoCo v2, the latter improving training stability and performance through architectural and augmentation enhancements. Training is optimized for distributed multi-GPU environments, using DistributedDataParallel for speed and simplicity. -
21
Typia
Super-fast/easy runtime validations and serializations
Super-fast/easy runtime validations and serializations through transformation. -
22
crkbd is the firmware and PCB design for the Corne split mechanical keyboard (aka "Corne"), maintained by foostan and the community. It provides QMK/VIA/Vial firmware support, RGB underglow, multiple layouts, and flexible hardware customization.
-
23
vJEPA-2
PyTorch code and models for VJEPA2 self-supervised learning from video
VJEPA2 is a next-generation self-supervised learning framework for video that extends the “predict in representation space” idea from i-JEPA to the temporal domain. Instead of reconstructing pixels, it predicts the missing high-level embeddings of masked space-time regions using a context encoder and a slowly updated target encoder. This objective encourages the model to learn semantics, motion, and long-range structure without the shortcuts that pixel-level losses can invite. The architecture is designed to scale: spatiotemporal ViT backbones, flexible masking schedules, and efficient sampling let it train on long clips while remaining stable. ... -
24
DeepSeek-OCR 2
Visual Causal Flow
DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. ... -
25
Kimi K2.5
Moonshot's most powerful AI model
...Designed for agentic workflows, it features an Agent Swarm mechanism that decomposes complex problems into coordinated sub-agents executing in parallel. With a 256K context length and MoonViT vision encoder, the model excels across reasoning, coding, long-context comprehension, image, and video benchmarks. Kimi K2.5 is available via Moonshot’s API (OpenAI/Anthropic-compatible) and supports deployment through vLLM, SGLang, and KTransformers.
