This repo contains the inference code to use pretrained human voice gender classifier. - You could also try Huggingface online demo. First, clone the original github repository and install the packages via pip. For those who need pretrained weights, please download it in here State-of-the-art speaker verification model already produces good representation of the speaker's gender. I used the pretrained ECAPA-TDNN from TaoRuijie's repository, added one linear layer to make two-class classifier, and finetuned the model with the VoxCeleb2 dev set. The model achieved 98.7% accuracy on the VoxCeleb1 identification test split. I would like to note the training dataset I've used for this model…
SAVRN Model Hub
Open-Weight Models
An open-weight model is an AI model whose trained weights are published for anyone to download. The weights are what the model learned in training. With a copy of them you can run the model on hardware you control and train it further on your own data.
Open weights are not the same as open source. Many publishers release the weights without the training data or code, and the license sets what you may do with the model. This library puts each model's full card, architecture, files, license and published evaluations on one page.
2,760Models
859Datasets
254Papers
1,692Publishers
5,040Sourced relationships
Updated 2026-09-18 · How the library is built
2,760 models, sorted by most downloaded.
EXAONE Tabular is a transformer-based foundation model for tabular data that solves classification and regression through in-context learning: you pass the labeled rows to fit and the model predicts new rows in a single forward pass — no gradient updates and no per-dataset training. This repository is the exaonetabular inference runtime — a self-contained package that loads a released checkpoint and serves predictions through a small, scikit-learn-style API. The code here is permissively licensed; the released weights are non-commercial — see Both checkpoints are released: EXAONETabularClassifier and EXAONETabularRegressor each fetch their own weights with a single frompretrained() call.…
VieNeu-TTS-v2 is the next generation of Vietnamese TTS, designed for Natural Communication, Podcasts, and Bilingual (En-Vi) Code-switching. This project features the flagship VieNeu-TTS-v2 architecture: Tác giả: Phạm Nguyễn Ngọc Bảo Training high-quality TTS models requires significant GPU resources. If you find this model useful, please consider supporting the development: Install the SDK to integrate VieNeu-TTS-0.3B into your research or applications: Deploy VieNeu-TTS as a high-performance API Server (powered by LMDeploy) with a single command. Start the Server with a Public Tunnel (No port forwarding needed): Once the server is running, you can connect from anywhere (Colab, Web Apps…
This is a BERT base cased model trained on SQuAD v2 Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to everyone!
FlowState is the first time-scale adjustable Time Series Foundation Model (TSFM), open-sourced by IBM Research. Combining an State Space Model (SSM) Encoder with a Functional Basis Decoder allows FlowState to transition into a timescale invariant coefficient space and make a continuous forecast from this space. This allows FlowState to seamlessly adjust to all possible sampling rates. Therefore, training in one time-scale helps for inference at all scales, allowing for drastically improved utilization of training data across time-scales. This innovation leads to a significant improvement in performance, making FlowState the new state-of-the art in zero-shot time series forecasting.…
VibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model (LLM) to understand textual…
03/18/2025 – We are releasing our 3B Orpheus TTS model with additional finetunes. Code is available on GitHub: CanopyAI/Orpheus-TTS Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances. Check out our Colab (link to Colab) or GitHub (link to GitHub) on how to run easy inference on our finetuned models. Do not use our models for impersonation without consent, misinformation or deception (including fake news or fraudulent calls), or any illegal or harmful activity. By…
This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-xsmall The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For futher evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification
GEnerative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue Gepard is a text-to-speech model built for real-time conversation. It starts speaking the moment text begins arriving, generating audio piece by piece instead of waiting for a full sentence — so it feels like a live voice, not a recording. It's a single language model that learned text and speech together, so the output carries natural rhythm and timing rather than the flat, stitched tone of older pipelines. The name evokes "Gepard"(/geh-PART/), German for cheetah — a nod to the model's low-latency, high-throughput streaming. - One clean pass per frame — the whole audio frame (32 orthogonal FSQ channels) is…
Toto (Time Series Optimized Transformer for Observability) is a state-of-the-art time-series foundation model designed for multi-variate time series forecasting, emphasizing observability metrics. Toto efficiently handles high-dimensional, sparse, and non-stationary data commonly encountered in observability scenarios. The average rank of Toto compared to the runner-up models on both the GIFT-Eval and BOOM benchmarks (as of May 19, 2025). - Tailored for Observability Metrics with State-of-the-Art Performance on GIFT-Eval and BOOM. Overview of Toto-Open-Base-1.0 architecture. Inference code is available on GitHub. For optimal speed and reduced memory usage, you should also install xFormers…
BEN2 (Background Erase Network) introduces a novel approach to foreground segmentation through its innovative Confidence Guided Matting (CGM) pipeline. The architecture employs a refiner network that targets and processes pixels where the base model exhibits lower confidence levels, resulting in more precise and reliable matting results. This model is built on BEN: BEN2 was trained on the DIS5k and our 22K proprietary segmentation dataset. Our enhanced model delivers superior performance in hair matting, 4K processing, object segmentation, and edge refinement. Our Base model is open source. To try the full model through our free web demo or integrate BEN2 into your project with our API…
TimesFM (Time Series Foundation Model) is a pretrained decoder-only model for time-series forecasting. This repository contains the Transformers port of the official TimesFM 2.5 PyTorch release. This model is converted from the official TimesFM 2.5 PyTorch checkpoint and integrated into transformers as TimesFm25ModelForPrediction. The converted checkpoint preserves the original architecture and forecasting behavior, including: patch-based inputs for time-series contexts decoder-only self-attention stack point and quantile forecasts Weight conversion parity is verified by comparing converted-model forecasts against the official implementation outputs on deterministic inputs.
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. 1. Unified and Scalable Model Family: A three-tier OCR model family spanning 1.5M to 34.5M parameters. PP-OCRv6medium achieves 86.2% detection Hmean and 83.2% recognition accuracy, outperforming PP-OCRv5server by +4.6% and +5.1%…
https://huggingface.co/facebook/bart-large-mnli with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
hfname: mul-eng - sourcelanguages: mul - targetlanguages: eng - opusreadmeurl: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/mul-eng/README.md - originalrepo: Tatoeba-Challenge - srcconstituents: {'sjnLatn', 'cat', 'nan', 'spa', 'ileLatn', 'pap', 'mwl', 'uzbLatn', 'mww', 'hil', 'lij', 'avkLatn', 'ladLatn', 'latLatn', 'bosLatn', 'oss', 'epo', 'ron', 'fry', 'cym', 'toiLatn', 'awa', 'swg', 'zsmLatn', 'zhoHant', 'gcfLatn', 'uzbCyrl', 'isl', 'lfnLatn', 'shsLatn', 'novLatn', 'bho', 'ltz', 'lzh', 'kurLatn', 'sun', 'arg', 'pesThaa', 'sqi', 'uigArab', 'csbLatn', 'fra', 'hat', 'livLatn', 'nonLatn', 'sco', 'cmnHans', 'pnb', 'roh', 'chv', 'ibo', 'bulLatn', 'amh', 'lfnCyrl'…
Model · Zero-shot classification
deberta-v3-xsmall-zeroshot-v1.1-all-33
This model was fine-tuned using the same pipeline as described in the model card for MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33 and in this paper. The foundation model is microsoft/deberta-v3-xsmall. The model only has 22 million backbone parameters and 128 million vocabulary parameters. The backbone parameters are the main parameters active during inference, providing a significant speedup over larger models. The model is 142 MB small. This model was trained to provide a small and highly efficient zeroshot option, especially for edge devices or in-browser use-cases with transformers.js. For usage instructions and other details refer to this model card…
UPDATED 8/21/2026 - The latest LTX Video-2.3 Uncensored Turbo v1.4 DiT with Distilled LoRA baked in. Modes: img2video, txt2video, FL2VA / T2VA / I2VA / REF2VA/ AUDIO-TO-VIDEO. A pre-merged, GGUF and FP8 build of LTX Video-2.3 with three fine-tunes baked into the weights: 1. Eros10 NSFW LoRA - Eros10 is known for high quality, coherence, and NSFW (1.0 strength) 2. DMD Distilled LoRA - DMD distilled LoRA promises faster generations, better facial preservation (I2V), and MUCH better instruction following than v1 or stock LTXV23. (1.0 strength) 3. LTX Video ICLoRA Detailer - Official LTXV In-Context LoRA for better reference image adherence. (0.6 strength) The model can produce video in as…
SegFormer model fine-tuned on ADE20k at resolution 640x640. It was introduced in the paper SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers by Xie et al. and first released in this repository. Disclaimer: The team releasing SegFormer did not write a model card for this model so this model card has been written by the Hugging Face team. SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmentation benchmarks such as ADE20K and Cityscapes. The hierarchical Transformer is first pre-trained on ImageNet-1k, after which a decode head is added and fine-tuned altogether on a…
NuExtract3 is a unified 4B vision-language reasoning model for document understanding. It combines strong structured information extraction with high-quality image-to-Markdown conversion, making it suitable for extraction pipelines, OCR, and RAG preprocessing for all types of documents such as scans, receipts, forms, invoices, contracts or tables. Try it out in the space! - Multilingual documents. - Reasoning and non-reasoning inference modes. - Template generation for structured extraction from natural language or input document. We benchmarked NuExtract on NuMind's internal structured benchmark, measuring model's performances on ~600 documents of diverse types including invoices, movie…
convert TurboWan2.1-T2V-1.3B-480P(https://modelscope.cn/models/TurboDiffusion/TurboWan2.1-T2V-1.3B-480P/summary) to TurboWan2.1-T2V-1.3B-Diffusers convert script https://github.com/IPostYellow/TurboWantoDiffusers/blob/main/convertturbowantodiffusers.py To use in sglang
A SegFormer-B4 model fine-tuned for human parsing with 18 semantic classes, optimized for fashion and virtual try-on applications. This model segments human images into 18 semantic categories including body parts (face, hair, arms, hands, legs, feet, torso), clothing items (top, dress, skirt, pants, belt, scarf), and accessories (bag, hat, glasses, jewelry). The pipeline automatically manages GPU/CPU and returns per-class masks at the original image resolution. For maximum accuracy, use our Python package which implements the exact preprocessing used during training: The package uses cv2.INTERAREA for resizing (matching training), while the HuggingFace pipeline uses PIL LANCZOS. Labels…
MeloTTS is a high-quality multi-lingual text-to-speech library by MyShell.ai. Supported languages include: - The Chinese speaker supports mixed Chinese and English. - Fast enough for CPU real-time inference. An unofficial live demo is hosted on Hugging Face Spaces. There are hundreds of TTS models on MyShell, much more than MeloTTS. See examples here. More can be found at the widget center of MyShell.ai. Follow the installation steps here before using the following snippet: Open Source AI Grant We are actively sponsoring open-source AI projects. The sponsorship includes GPU resources, fundings and intellectual support (collaboration with top research labs). We welcome both reseach and…
This model is a fine-tuned version of YOLOv8x specialized in detecting two specific classes: Face and Person. It has been trained on a large-scale proprietary dataset consisting of approximately 150,000 images. The high capacity of the YOLOv8x architecture combined with a diverse proprietary dataset ensures high accuracy and robustness in various scenarios. You can load the model using the Hugging Face transformers library by enabling custom code execution. If you prefer the standard Ultralytics API, you can download the weights from the Hub and load them directly. This method automatically handles model downloading for ultralytics YOLO model. This model is based on the Ultralytics YOLOv8…
Model Collections
Hand-picked starting points, each with the reason it exists.
Collection · 4 entries
Embedding models for retrieval
Sentence and document embedding models used to build retrieval systems. Dimension and sequence length matter more than size here, and both come from the publisher.
Collection · 4 entries
Models that fit on one accelerator
Models whose publisher-reported parameter count puts them within reach of a single accelerator at common precisions. Memory needed depends on precision and serving configuration, so treat the parameter count as the starting point, not the answer.
Collection · 6 entries
Open-weight text models worth knowing
Widely used open-weight language models, chosen because each one is a distinct family rather than a variant of the one above it. Selection, not a ranking.
Collection · 3 entries
Speech and audio models
Recognition and synthesis models, grouped so the two directions are easy to compare.
Open-Weight Models Explained
What is an open-weight model?
An AI model whose trained weights are published for anyone to download, so it can be run, tested and fine-tuned on hardware the user controls.
Is an open-weight model the same as open source?
Not always. Open weights means the trained model can be downloaded. Open source usually also means the training code and data are available and the license allows broad reuse. Many open-weight models release the weights only.
Can I use an open-weight model commercially?
It depends on the license. Apache 2.0 and MIT allow commercial use. Other licenses limit it, for example to non-commercial use or below a set number of users. Every model page here shows its license.
How much memory does an open-weight model need?
About two bytes per parameter at 16-bit precision, so a 7-billion-parameter model needs roughly 14 GB for its weights, plus memory for the context it processes. Each model page lists its parameter count and the size of its files.
Related SAVRN Research
The hub sits beside SAVRN's market data and infrastructure research: what models cost to run, and what it takes to run them.
SAVRN Index
What open models cost to run
The same open-weight model priced by every host that serves it, per million tokens.
Research Hub
Data center trackers and maps
Moratoriums, permits, power, water and capital behind the facilities that run these models.
Method
How the Model Hub is built
Sources, evidence labels, refresh behaviour, and the limits of every comparison here.