Search Results for "encoder" - Page 3
Sort By:
Showing 81 open source projects for "encoder"
View related business solutions-
Earn up to 16% annual interest with Nexo.Generate interest, access liquidity without selling, and execute trades seamlessly. All in one platform. Geographic restrictions, eligibility, and terms apply.
-
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
1
Denoiser
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)
Denoiser is a real-time speech enhancement model operating directly on raw waveforms, designed to clean noisy audio while running efficiently on CPU. It uses a causal encoder-decoder architecture with skip connections, optimized with losses defined both in the time domain and frequency domain to better suppress noise while preserving speech. Unlike models that operate on spectrograms alone, this design enables lower latency and coherent waveform output. The implementation includes data augmentation techniques applied to the raw waveforms (e.g. noise mixing, reverberation) to improve model robustness and generalization to diverse noise types. ... -
2
TTS
Deep learning for text to speech
...Notebooks for extensive model benchmarking. Modular (but not too much) code base enabling easy testing for new ideas. Text2Spec models (Tacotron, Tacotron2, Glow-TTS, SpeedySpeech). Speaker Encoder to compute speaker embeddings efficiently. Vocoder models (MelGAN, Multiband-MelGAN, GAN-TTS, ParallelWaveGAN, WaveGrad, WaveRNN). If you are only interested in synthesizing speech with the released TTS models, installing from PyPI is the easiest option. -
3
ALAE
Adversarial Latent Autoencoders
...The project implements the architecture introduced in the CVPR research paper on Adversarial Latent Autoencoders, which focuses on improving generative modeling by learning latent representations aligned with adversarial training objectives. Unlike traditional GANs that directly generate images from random noise, ALAE uses an encoder-decoder architecture that maps images into a structured latent space and then reconstructs them through adversarial training. This design allows the model to learn interpretable latent representations that can be manipulated to control generated image attributes. -
4
Multilingual Speech Synthesis
An implementation of Tacotron 2 that supports multilingual experiments
...The first shares the whole encoder and uses an adversarial classifier to remove speaker-dependent information from the encoder. The second has separate encoders for each language. -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
5
DETR
End-to-end object detection with transformers
...Unlike traditional computer vision techniques, DETR approaches object detection as a direct set prediction problem. It consists of a set-based global loss, which forces unique predictions via bipartite matching, and a Transformer encoder-decoder architecture. Given a fixed small set of learned object queries, DETR reasons about the relations of the objects and the global image context to directly output the final set of predictions in parallel. Due to this parallel nature, DETR is very fast and efficient. -
6
Texar
Toolkit for Machine Learning, Natural Language Processing
Texar is a toolkit aiming to support a broad set of machine learning, especially natural language processing and text generation tasks. Texar provides a library of easy-to-use ML modules and functionalities for composing whatever models and algorithms. The tool is designed for both researchers and practitioners for fast prototyping and experimentation. Texar was originally developed and is actively contributed by Petuum and CMU in collaboration with other institutes. A mirror of this... -
7
CakeChat
CakeChat: Emotional Generative Dialog System
...The code is flexible and allows to condition model's responses by an arbitrary categorical variable. For example, you can train your own persona-based neural conversational model or create an emotional chatting machine. Hierarchical Recurrent Encoder-Decoder (HRED) architecture for handling deep dialog context. Multilayer RNN with GRU cells. The first layer of the utterance-level encoder is always bidirectional. By default, CuDNNGRU implementation is used for ~25% acceleration during inference. Thought vector is fed into decoder on each decoding step. Decoder can be conditioned on any categorical label, for example, emotion label or persona id. ... -
8
Butteraugli
Estimates the psychovisual difference between two images
...These maps make it practical to tune compressor settings and confirm whether bitrate reductions are visually acceptable. The metric has become a common yardstick for objective image quality when comparing codecs or encoder tweaks that target web or mobile delivery. Because it is deterministic and fast, it can be used in automated pipelines to gate releases on visual quality, not just file size. -
9
SG2Im
Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 201
...This separation lets the model reason about geometry and composition before committing to texture and color, improving spatial fidelity. The repository includes training code, datasets, and evaluation scripts so researchers can reproduce baselines and extend components such as the graph encoder or image generator. In practice, sg2im demonstrates how structured semantics can guide generative models to produce controllable, compositional imagery. -
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.
-
10
OpenSeq2Seq
Toolkit for efficient experimentation with Speech Recognition
OpenSeq2Seq is a TensorFlow-based toolkit for efficient experimentation with sequence-to-sequence models across speech and NLP tasks. Its core goal is to give researchers a flexible, modular framework for building and training encoder–decoder architectures while fully leveraging distributed and mixed-precision training. The toolkit includes ready-made models for neural machine translation, automatic speech recognition, speech synthesis, language modeling, and additional NLP tasks such as sentiment analysis. It supports multi-GPU and multi-node data-parallel training, and integrates with Horovod to scale out across large GPU clusters. ... -
11
Retrieval-Based Conversational Model
Dual LSTM Encoder for Dialog Response Generation
Retrieval-Based Conversational Model in Tensorflow is a project implementing a retrieval-based conversational model using a dual LSTM encoder architecture in TensorFlow, illustrating how neural networks can be trained to select appropriate responses from a fixed set of candidate replies rather than generate them from scratch. The core idea is to embed both the conversation context and potential replies into vector representations, then score how well each candidate fits the current dialogue, choosing the best match accordingly. ... -
12
Ministral 3 8B Instruct 2512
Compact 8B multimodal instruct model optimized for edge deployment
Ministral 3 8B Instruct 2512 is a balanced, efficient model in the Ministral 3 family, offering strong multimodal capabilities within a compact footprint. It combines an 8.4B-parameter language model with a 0.4B vision encoder, enabling both text reasoning and image understanding. This FP8 instruct-fine-tuned variant is optimized for chat, instruction following, and structured outputs, making it ideal for daily assistant tasks and lightweight agentic workflows. Designed for edge deployment, the model can run on a wide range of hardware and fits locally on a single 12GB GPU, with the option for even smaller quantized configurations. ... -
13
Qwen-Image-Edit
An advanced bilingual image editing with semantic control
Qwen-Image-Edit is the image editing extension of Qwen-Image, a 20B parameter model that combines advanced visual and text-rendering capabilities for creative and precise editing. It leverages both Qwen2.5-VL for semantic control and a VAE Encoder for appearance control, enabling users to edit at both the content and detail level. The model excels at semantic edits like style transfer, object rotation, and novel view synthesis, while also handling precise appearance edits such as adding or removing elements without altering surrounding regions. A standout feature is its bilingual text editing in English and Chinese, which preserves original font, size, and style during modifications. ... -
14
Mistral Large 3 675B Base 2512
Frontier-scale 675B multimodal base model for custom AI training
...The model is engineered for reliability, long-context comprehension, and stable performance across many enterprise, scientific, and knowledge-intensive workloads. Its architecture includes a powerful language MoE and a 2.5B-parameter vision encoder, enabling multimodal understanding out of the box. Mistral Large 3 Base supports deployment on-premises using FP8 or NVFP4 formats, enabling high-performance workflows on B200, H200, H100, or A100 hardware. -
15
Mistral Large 3 675B Instruct 2512 Eagle
Speculative-decoding accelerator for the 675B Mistral Large 3
...It works alongside the primary 675B instruct model, enabling faster response times by predicting several tokens ahead using Mistral’s Eagle speculative method. Built on the same frontier-scale multimodal Mixture-of-Experts architecture, it complements a system featuring 41B active parameters and a 2.5B-parameter vision encoder. The Eagle variant is specialized rather than standalone, serving as a performance accelerator for production-grade assistants, agentic workflows, long-context applications, and retrieval-augmented reasoning pipelines. It supports the same multilingual, system-prompt-aligned, and function-calling behavior as the main instruct model when used in the recommended server-client configuration. -
16
Mistral Large 3 675B Instruct 2512 NVFP4
Quantized 675B multimodal instruct model optimized for NVFP4
...It retains the same instruction-tuned behavior as the FP8 model, making it ideal for production assistants, agentic workflows, scientific tasks, and long-context enterprise systems. The model integrates a 673B-parameter MoE language backbone with a 2.5B-parameter vision encoder, enabling rich multimodal analysis across text and images. Designed for efficient deployment, it runs on a single H100 or A100 node in NVFP4 while delivering performance similar to FP8 for short- and mid-context workloads. -
17
Ministral 3 3B Base 2512
Small 3B-base multimodal model ideal for custom AI on edge hardware
Ministral 3 3B Base 2512 is the smallest model in the Ministral 3 family, offering a compact yet capable multimodal architecture suited for lightweight AI applications. It combines a 3.4B-parameter language model with a 0.4B vision encoder, enabling both text and image understanding in a tiny footprint. As the base pretrained model, it is not fine-tuned for instructions or reasoning, making it the ideal foundation for custom post-training, domain adaptation, or specialized downstream tasks. The model is fully optimized for edge deployment and can run locally on a single GPU, fitting in 16GB VRAM in BF16 or less than 8GB when quantized. ... -
18
Ministral 3 8B Reasoning 2512
Efficient 8B multimodal model tuned for advanced reasoning tasks.
Ministral 3 8B Reasoning 2512 is a balanced midsize model in the Ministral 3 family, delivering strong multimodal reasoning capabilities within an efficient footprint. It combines an 8.4B-parameter language model with a 0.4B vision encoder, enabling it to process both text and images for advanced reasoning tasks. This version is specifically post-trained for reasoning, making it well-suited for math, coding, and STEM applications requiring multi-step logic and problem-solving. Despite its reasoning-focused training, the model remains edge-optimized and can run locally on a single 24GB GPU in BF16, or under 12GB when quantized. ... -
19
Ministral 3 14B Reasoning 2512
High-precision 14B multimodal model built for advanced reasoning tasks
Ministral 3 14B Reasoning 2512 is the largest model in the Ministral 3 series, delivering frontier-level performance with capabilities comparable to the Mistral Small 3.2 24B model. It pairs a 13.5B-parameter language model with a 0.4B vision encoder, enabling strong multimodal reasoning across both text and images. This version is specifically post-trained for reasoning tasks, making it highly effective for math, coding, STEM workloads, and complex multi-step problem-solving. Despite its scale, the model is engineered for practical deployment and can run locally on 32GB of VRAM in BF16 or under 24GB when quantized. ... -
20
Ministral 3 3B Instruct 2512
Ultra-efficient 3B multimodal instruct model built for edge deployment
Ministral 3 3B Instruct 2512 is the smallest model in the Ministral 3 family, offering a lightweight yet capable multimodal architecture designed for edge and low-resource deployments. It includes a 3.4B-parameter language model paired with a 0.4B vision encoder, enabling it to understand both text and visual inputs. As an FP8 instruct-fine-tuned model, it is optimized for chat, instruction following, and compact agentic tasks while maintaining strong adherence to system prompts. Despite its small size, it delivers efficient real-time performance and can run locally on a single 8GB GPU, with further memory reductions through quantization. ... -
21
Ministral 3 14B Instruct 2512
Efficient 14B multimodal instruct model with edge deployment and FP8
Ministral 3 14B Instruct 2512 is the largest model in the Ministral 3 family, delivering frontier performance comparable to much larger systems while remaining optimized for edge-level deployment. It combines a 13.5B-parameter language model with a 0.4B-parameter vision encoder, enabling strong multimodal understanding in both text and image tasks. This FP8 instruct-tuned variant is designed specifically for chat, instruction following, and agentic workflows with robust system-prompt adherence. Despite its size, the model is engineered for practical deployment, capable of running locally on a single 24GB GPU when served in FP8 and even less with further quantization. ... -
22
Mistral Large 3 675B Instruct 2512
Frontier-scale 675B multimodal instruct MoE model for enterprise AIMis
...As the instruct-tuned FP8 variant, it is optimized for reliable instruction following, agentic workflows, production-grade assistants, and long-context enterprise tasks. It incorporates a massive 673B-parameter language MoE backbone and a 2.5B-parameter vision encoder, enabling rich multimodal understanding across text and images. The model supports dozens of languages and maintains strong system-prompt adherence, making it suitable for global and structured enterprise use. Designed for high performance, it runs on a single node of B200 or H200 GPUs in FP8, and can also operate in NVFP4 mode on H100 or A100 hardware. ... -
23
Ministral 3 3B Reasoning 2512
Compact 3B-param multimodal model for efficient on-device reasoning
Ministral 3 3B Reasoning 2512 is the smallest reasoning-capable model in the Ministal-3 family, yet delivers a surprisingly capable multimodal and multilingual base for lightweight AI applications. It pairs a 3.4B-parameter language model with a 0.4B-parameter vision encoder, enabling it to understand both text and image inputs. This reasoning-tuned variant is optimized for tasks like math, coding, and other STEM-related problem solving, making it suitable for applications that require logical reasoning, analysis, or structured thinking. Despite its modest size, the model is designed for edge deployment and can run locally, fitting in ~16 GB of VRAM in BF16 or under 8 GB of RAM/VRAM when quantized. ... -
24
Ministral 3 8B Base 2512
Versatile 8B-base multimodal LLM, flexible foundation for custom AI
Ministral 3 8B Base 2512 is a mid-sized, dense model in the Ministral 3 series, designed as a general-purpose foundation for text and image tasks. It pairs an 8.4B-parameter language model with a 0.4B-parameter vision encoder, enabling unified multimodal capabilities out of the box. As a “base” model (i.e., not fine-tuned for instruction or reasoning), it offers a flexible starting point for custom downstream tasks or fine-tuning. The model supports a large 256k token context window, making it capable of handling long documents or extended dialogues. ... -
25
Ministral 3 14B Base 2512
Powerful 14B-base multimodal model — flexible base for fine-tuning
Ministral 3 14B Base 2512 is the largest model in the Ministral 3 line, offering state-of-the-art language and vision capabilities in a dense, base-pretrained form. It combines a 13.5B-parameter language model with a 0.4B-parameter vision encoder, enabling both high-quality text understanding/generation and image-aware tasks. As a “base” model (i.e. not fine-tuned for instruction or reasoning), it provides a flexible foundation ideal for custom fine-tuning or downstream specialization. The model remains efficient enough for on-prem or local deployment — it fits in ~32 GB VRAM in BF16, and requires under ~24 GB when quantized. ...
