Search Results for "encoder"
Sort By:
Showing 80 open source projects for "encoder"
View related business solutions-
The Most Powerful Software Platform for EHSQ and ESG ManagementChoose from a complete set of software solutions across EHSQ that address all aspects of top performing Environmental, Health and Safety, and Quality management programs.
-
Skillfully - The future of skills based hiringSkillfully transforms hiring through AI-powered skill simulations that show you how candidates actually perform before you hire them. Our platform helps companies cut through AI-generated resumes and rehearsed interviews by validating real capabilities in action. Through dynamic job specific simulations and skill-based assessments, companies like Bloomberg and McKinsey have cut screening time by 50% while dramatically improving hire quality.
-
1
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. -
2
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. -
3
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. -
4
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... -
Secure your business by securing your people.Take the guesswork out of password management, shadow IT, infrastructure, and secret sharing so you can keep your people safe and your business moving.
-
5
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. -
6
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. ... -
7
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. -
8
Real-Time Voice Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Real-Time Voice Cloning is an influential deep-learning repository that demonstrates how to clone a voice from just a few seconds of audio and then generate arbitrary speech in that voice in near real time. It implements the SV2TTS pipeline (“Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis”) in three stages: a speaker encoder, a synthesizer, and a vocoder. In the first stage, short audio clips are converted into a fixed-dimensional speaker embedding that captures voice characteristics; this embedding is then used by a Tacotron-style synthesizer to generate spectrograms from text, which a WaveRNN-based vocoder finally turns into audio. The repo includes both a command-line demo and a graphical “toolbox” application where you can load reference voices, type text, and hear the synthesized results interactively. ... -
9
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. -
Cloud-Based Software Licensing - Zentitle by Nalpeiron1000’s software companies have used Zentitle to launch new software products fast and control their entitlements easily - many going from startup to IPO on our platform. Our software monetization infrastructure allows you to easily build or
-
10
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. -
11
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. -
12
FireRedASR
Open-source industrial-grade ASR models
FireRedASR is an industrial-grade family of open-source automatic speech recognition models designed to provide high-precision speech-to-text performance across languages including Mandarin, English, and various Chinese dialects, achieving new state-of-the-art benchmarks on public test sets. The project includes multiple model variants to meet different application needs, such as high-accuracy end-to-end interaction using an encoder-adapter-LLM framework and efficient real-time recognition using attention-based encoder-decoder architectures, giving developers flexibility in balancing performance and resource constraints. FireRedASR not only excels in traditional speech recognition tasks but also demonstrates strong capability in challenging scenarios like singing lyrics recognition, where accurate transcription is often difficult for conventional models. -
13
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. ... -
14
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. -
15
Perception Models
State-of-the-art Image & Video CLIP, Multimodal Large Language Models
Perception Models is a state-of-the-art framework developed by Facebook Research for advanced image and video perception tasks. It introduces two primary components: the Perception Encoder (PE) for visual feature extraction and the Perception Language Model (PLM) for multimodal decoding and reasoning. The PE module is a family of vision encoders designed to excel in image and video understanding, surpassing models like SigLIP2, InternVideo2, and DINOv2 across multiple benchmarks. Meanwhile, PLM integrates with PE to power vision-language modeling, achieving results competitive with leading multimodal systems such as QwenVL2.5 and InternVL3, all while being fully reproducible with open data. ... -
16
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. ... -
17
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. ... -
18
GLM-OCR
Accurate × Fast × Comprehensive
GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B), enabling deployment in high-concurrency services and edge environments. ... -
19
x-transformers
A simple but complete full-attention transformer
A simple but complete full-attention transformer with a set of promising experimental features from various papers. Proposes adding learned memory key/values prior to attending. They were able to remove feedforwards altogether and attain a similar performance to the original transformers. I have found that keeping the feedforwards and adding the memory key/values leads to even better performance. Proposes adding learned tokens, akin to CLS tokens, named memory tokens, that is passed through... -
20
DeepSeek VL
Towards Real-World Vision-Language Understanding
...It enables understanding and generation across visual and textual modalities—meaning it can process an image + a prompt, answer questions about images, caption, classify, or reason about visuals in context. The model is likely used internally as the visual encoder backbone for agent use cases, to ground perception in downstream tasks (e.g. answering questions about a screenshot). The repository includes model weights (or pointers to them), evaluation metrics on standard vision + language benchmarks, and configuration or architecture files. It also supports inference tools for forwarding image + prompt through the model to produce text output. ... -
21
FLUX.2
Official inference repo for FLUX.2 models
...It supports high-resolution output (up to ~4 megapixels), which allows for photography-quality images, detailed product shots, infographics or UI mockups rather than just low-resolution drafts. FLUX.2 is built with a modern architecture (a flow-matching transformer + a revamped VAE + a strong vision-language encoder), enabling strong prompt adherence, correct rendering of text/typography in images, reliable lighting, layout, and physical realism, and consistent style/character/product identity across multiple generations or edits. -
22
AV1 AVIF
AV1 Image File Format Specification - ISO-BMFF/HEIF derivative
...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 a versatile, modern image format suitable for both simple photos and advanced imagery needing high fidelity. The specification ensures interoperability across encoders and decoders, providing guidelines so that images created by any compliant AVIF encoder can be reliably decoded by compliant decoders. As adoption grows, AV1 AVIF plays a crucial role in promoting a royalty-free, open, high-efficiency image standard that competes with older formats such as JPEG and newer proprietary ones. -
23
Ultravox
Fast multimodal LLM for real-time voice interaction and AI apps
Ultravox is an open source multimodal large language model designed specifically for real-time voice-based interactions. It is built to process both text and spoken audio directly, eliminating the need for a separate speech recognition stage and enabling more seamless conversational experiences. Ultravox works by combining text prompts with encoded audio inputs, allowing it to understand spoken language alongside written instructions in a unified pipeline. Internally, it leverages pretrained... -
24
Qwen-2.5-VL
Qwen2.5-VL is the multimodal large language model series
Qwen2.5 is a series of large language models developed by the Qwen team at Alibaba Cloud, designed to enhance natural language understanding and generation across multiple languages. The models are available in various sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B parameters, catering to diverse computational requirements. Trained on a comprehensive dataset of up to 18 trillion tokens, Qwen2.5 models exhibit significant improvements in instruction following, long-text generation... -
25
FlagEmbedding
Retrieval and Retrieval-augmented LLMs
...The toolkit provides infrastructure for inference, fine-tuning, evaluation, and dataset preparation, enabling developers to train custom embedding models for specific domains or applications. It also includes reranker models that refine search results by re-evaluating candidate documents using cross-encoder architectures, improving retrieval accuracy in complex queries.
