Search public pages, research tools, and SAVRN solutions.
SAVRN Model Hub · Models by License
72 open-weight models released under Creative Commons Attribution-NonCommercial 4.0 in the SAVRN Model Hub, with AI at Meta, Multimedia Computing Group-Nanjing University and Salesforce AI Research publishing the most.
CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder. Read the license text.
Credit the rights holder and stay non-commercial, and Creative Commons Attribution-NonCommercial 4.0 lets you share and adapt the work. The second condition decides deployments. Commercial use is not permitted without separate permission from the rights holder, so a model under these terms can run in your own racks for non-commercial work, but the moment it serves a paying customer or backs a product you bill for, that permission has to be in hand, in writing, before the weights touch production.
Nothing about the hardware slows you down. The most downloaded model here, mms-300m-1130-forced-aligner at 2,609,459 downloads a month, is 315M parameters and needs 0.8 GB at 16-bit. jina-embeddings-v3, second at 1,957,393, is 572M parameters with an 8,194 token context in 1.4 GB, and jina-reranker-v3 fits a 131,072 token context in the same 1.4 GB. The cheapest host on the Index for all three is a single MI300X at $1.85 an hour. One accelerator, not a rack; the license is the hard part.
AI at Meta publishes the most under these terms, 20 of the 72, including musicgen-medium at 1,952,754 downloads and nllb-200-distilled-600M at 1,135,320. The Multimedia Computing Group at Nanjing University has 10, Salesforce AI Research 8, PyTorch Image Models 6, Jina AI and OpenGVLab 4 each. Video classification leads the task list at 21 models, audio classification at 10 and text to speech at 9: a media and speech license more than a chat-model license.
| Model | Publisher | Parameters | License | Monthly downloads | Cheapest GPUs at 16-bit |
|---|---|---|---|---|---|
| mms-300m-1130-forced-aligner | Mahmoud Ashraf | 315M | cc-by-nc-4.0 | 2.6M | 1x MI300X, $1.85/hr |
| jina-embeddings-v3 | Jina AI | 572M | cc-by-nc-4.0 | 2M | 1x MI300X, $1.85/hr |
| musicgen-medium | AI at Meta | — | cc-by-nc-4.0 | 2M | — |
| wav2vec2-base-vi-vlsp2020 | Binh Nguyen | — | cc-by-nc-4.0 | 1.3M | — |
| nllb-200-distilled-600M | AI at Meta | — | cc-by-nc-4.0 | 1.1M | — |
| jina-reranker-v2-base-multilingual | Jina AI | 278M | cc-by-nc-4.0 | 1.1M | 1x MI300X, $1.85/hr |
| F5-TTS | Yushen CHEN | — | cc-by-nc-4.0 | 984.3k | — |
| jina-reranker-v3 | Jina AI | 597M | cc-by-nc-4.0 | 782.2k | 1x MI300X, $1.85/hr |
| open-vakgyata | OneCXi | 59M | cc-by-nc-4.0 | 500.7k | 1x MI300X, $1.85/hr |
| fasttext-language-identification | AI at Meta | — | cc-by-nc-4.0 | 437k | — |
| Publisher | Models |
|---|---|
| AI at Meta | 20 |
| Multimedia Computing Group-Nanjing University | 10 |
| Salesforce AI Research | 8 |
| PyTorch Image Models | 6 |
| OpenGVLab | 4 |
| Jina AI | 4 |
This Python package provides an efficient way to perform forced alignment between text and audio using Hugging Face's pretrained models. it also features an improved implementation to use much less memory than TorchAudio forced alignment API. The model checkpoint uploaded here is a conversion from torchaudio to HF Transformers for the MMS-300M checkpoint trained on forced alignment dataset
jina-embeddings-v3 is a multilingual multi-task text embedding model designed for a variety of NLP applications. Based on the Jina-XLM-RoBERTa architecture, this model supports Rotary Position Embeddings to handle long input sequences up to 8192 tokens. Additionally, it features 5 LoRA adapters to generate task-specific embeddings efficiently. - retrieval.query: Used for query embeddings in asymmetric retrieval tasks - retrieval.passage: Used for passage embeddings in asymmetric retrieval tasks - separation: Used for embeddings in clustering and re-ranking applications - classification: Used for embeddings in classification tasks - text-matching: Used for embeddings in tasks that quantify…
The Jina Reranker v2 (jina-reranker-v2-base-multilingual) is a transformer-based model that has been fine-tuned for text reranking task, which is a crucial component in many information retrieval systems. It is a cross-encoder model that takes a query and a document pair as input and outputs a score indicating the relevance of the document to the query. The model is trained on a large dataset of query-document pairs and is capable of reranking documents in multiple languages with high accuracy. Compared with the state-of-the-art reranker models, including the previous released jina-reranker-v1-base-en, the Jina Reranker v2 model has demonstrated competitiveness across a series of benchmarks…
jina-reranker-v3 is a 0.6B parameter multilingual document reranker with a novel last but not late interaction architecture. Unlike ColBERT's separate encoding with multi-vector matching, this model performs causal self-attention between query and documents within the same context window, extracting contextual embeddings from the last token of each document. Built on Qwen3-0.6B with 28 transformer layers and a lightweight MLP projector (1024→512→256), it processes up to 64 documents simultaneously within 131K token context. The model achieves state-of-the-art BEIR performance with 61.94 nDCG@10 while being 10× smaller than generative listwise rerankers. Use transformers for local inference…
VideoMAE model pre-trained on Kinetics-400 for 1600 epochs in a self-supervised way. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to the model as a sequence of…
pipelinetag: text-classification - sentence-transformers - vidore - reranker - qwen2vl - multilingual basemodel: libraryname: transformers jina-reranker-m0 is our new multilingual multimodal reranker model for ranking visual documents across multiple languages: it accepts a query alongside a collection of visually rich document images, including pages with text, figures, tables, infographics, and various layouts across multiple domains and over 29 languages. It outputs a ranked list of documents ordered by their relevance to the input query. Compared to jina-reranker-v2-base-multilingual, jina-reranker-m0 also improves text reranking for multilingual content, long documents, and code…
This is the official repository for the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization". For more detailed information, we strongly recommend referring to https://github.com/tencent-ailab/MuQ and the paper). In this repo, the following models are released: - MuQ(see this link): A large music foundation model pre-trained via Self-Supervised Learning (SSL), achieving SOTA in various MIR tasks. - MuQ-MuLan(see this link): A music-text joint embedding model trained via contrastive learning, supporting both English and Chinese texts. To begin with, please use pip to install the official muq lib, and ensure that your python>=3.8: To extract music…
SeamlessM4T is our foundational all-in-one Massively Multilingual and Multimodal Machine Translation model delivering high-quality translation for speech and text in nearly 100 languages. SeamlessM4T models support the tasks of: - Automatic speech recognition (ASR). - 101 languages for speech input. - 96 Languages for text input/output. - 35 languages for speech output. We are releasing SeamlessM4T v2, an updated version with our novel UnitY2 architecture. This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks. The v2 version of SeamlessM4T is a multitask adaptation of our novel UnitY2 architecture. Unity2 with its hierarchical…
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
mms - vits pipelinetag: text-to-speech This repository contains the English (eng) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. MMS-TTS is available in the Transformers library from version 4.33 onwards. VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a speech…
mms - vits pipelinetag: text-to-speech This repository contains the Bamanankan (bam) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. MMS-TTS is available in the Transformers library from version 4.33 onwards. VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a speech…
Moirai 2.0 is a decoder-only universal time series forecasting transformer model pre-trained on: - Subset of GIFT-Eval Pretrain, and Train datasets (Non-leaking historical context). - Mixup data generated from non-leaking subsets of Chronos Dataset. - Synthetic time series produced via KernelSynth introduced in Chronos paper. - Internal Salesforce operational data. We make significant improvements over the first version of Moirai (please refer to the paper for previous version): - Switched from a distributional loss to a quantile loss formulation. - Moved from single-token to multi-token prediction, improving efficiency and stability. - Added a data filtering mechanism to filter out…
Nougat model trained on PDF-to-markdown. It was introduced in the paper Nougat: Neural Optical Understanding for Academic Documents by Blecher et al. and first released in this repository. Disclaimer: The team releasing Nougat did not write a model card for this model so this model card has been written by the Hugging Face team. Note: this model corresponds to the "0.1.0-base" version of the original repository. Nougat is a Donut model trained to transcribe scientific PDFs into an easy-to-use markdown format. The model consists of a Swin Transformer as vision encoder, and an mBART model as text decoder. The model is trained to autoregressively predict the markdown given only the pixels of…
Model · Video classification
VideoMAE model pre-trained for 1600 epochs in a self-supervised way and fine-tuned in a supervised way on Kinetics-400. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to…
MusicGen is a text-to-music model capable of genreating high-quality music samples conditioned on text descriptions or audio prompts. It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods, like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio. MusicGen was published in Simple and Controllable Music Generation by Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant…
Our models use wav2vec2 architecture, pre-trained on 13k hours of Vietnamese youtube audio (un-label data) and fine-tuned on 250 hours labeled of VLSP ASR dataset on 16kHz sampled speech audio. You can find more description here The ASR model parameters are made available for non-commercial use only, under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. You can find details at: https://creativecommons.org/licenses/by-nc/4.0/legalcode [email protected]
This is the model card of NLLB-200's distilled 600M variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200…
Download F5-TTS or E2 TTS and place under ckpts/ Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
open-vakgyata is an open-source language identification model capable of detecting and classifying indian languages from speech inputs. Specification If you use this model in your research or application, please consider citing the model and its base source
fastText is an open-source, free, lightweight library that allows users to learn text representations and text classifiers. It works on standard, generic hardware. Models can later be reduced in size to even fit on mobile devices. It was introduced in this paper. The official website can be found here. This LID (Language IDentification) model is used to predict the language of the input text, and the hosted version (lid218e) was released as part of the NLLB project and can detect 217 languages. You can find older versions (ones that can identify 157 languages) on the official fastText website. fastText is a library for efficient learning of word representations and sentence classification.…
This is the model card of NLLB-200's distilled 1.3B variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200…
This is the model card of NLLB-200's 3.3B variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200 model was…
Download F5-TTS or E2 TTS and place under ckpts/ Paper: E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-1k. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
VieNeu-TTS-0.3B-Q4-0-GGUF is a Q40 quantized version of VieNeu-TTS-0.3B. This model is specifically optimized to run directly on the CPU, providing extremely fast speech synthesis without the need for a dedicated GPU. Training high-quality TTS models requires significant GPU resources. If you find this model useful, please consider supporting the development: eSpeak NG is mandatory for phonemization. Use the source code from GitHub for the best experience with full text preprocessing support: In the UI, select Backbone: VieNeu-TTS-0.3B-q4-gguf and Device: CPU. Install the SDK to integrate VieNeu-TTS-0.3B into your research or applications: This model is released under the CC BY-NC 4.0…
The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M, trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm. Here is a table for quick model pick-up: The m-a-p models…
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Pretrained on Instagram-1B hashtags dataset using semi-weakly supervised learning and fine-tuned on ImageNet-1k by paper authors. - Billion-scale semi-supervised learning for image classification: https://arxiv.org/abs/1905.00546 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.
SeamlessM4T is a collection of models designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text. This repository hosts Hugging Face's implementation of SeamlessM4T. You can find the original weights, as well as a guide on how to run them in the original hub repositories (large and medium checkpoints). SeamlessM4T v2, an improved version of this version with a novel architecture, has been released here. This new model improves over SeamlessM4T v1 in quality as well as inference speed in speech generation tasks. SeamlessM4T v2 is also supported by Transformers, more on it in the model card of this…
The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M, trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm. Here is a table for quick model pick-up: The m-a-p models…
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 1024 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 1024 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 1024 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to…
A ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-1k. Explore the dataset and runtime metrics of this model in timm model results. All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.
This is the official repository for the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization". For more detailed information, we strongly recommend referring to https://github.com/tencent-ailab/MuQ and the paper). In this repo, the following models are released: - MuQ(see this link): A large music foundation model pre-trained via Self-Supervised Learning (SSL), achieving SOTA in various MIR tasks. - MuQ-MuLan(see this link): A music-text joint embedding model trained via contrastive learning, supporting both English and Chinese texts. To begin with, please use pip to install the official muq lib, and ensure that your python>=3.8: Using MuQ-MuLan to…
This is the model card of NLLB-200's 1.3B variant. Here are the metrics for that particular checkpoint. - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper. - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022 - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues • Model performance measures: NLLB-200 model was…
This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 126 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 126 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 126 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to have…
F5-TTSRUSSIAN - дообученная версия оригинальной модели F5-TTS, адаптированная для синтеза русской речи. Демо: демо работы модели (F5-TTSRUSSIAN/F5TTSv1Base) и сравнение с XTTS и FishSpeech — F5-TTSRUSSIAN/F5TTSv1Base — первая версия модели, использованная для генерации демо-записей. F5-TTSRUSSIAN/F5TTSv1Baseaccenttune — дообученная версия с полной разметкой ударений (100% предложений в обучающем датасете). Рекомендуется использовать символы ударения для лучшего качества синтеза. F5-TTSRUSSIAN/F5TTSv1Basev2 — дообученная версия (+16 эпох). Добавлена фильтрация данных (удалено ~5% записей с артефактами, soft-clean), с полной разметка ударений в тексте.
This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-base). The Moirai-1.1-R model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with…
GGUF weights for omnivoice.cpp, a C++17/GGML port of OmniVoice (k2-fsa/OmniVoice). Multilingual zero shot TTS, 646 languages, 24 kHz mono. Runs on CPU, CUDA, ROCm, Metal, Vulkan. omnivoice-base-{variant}.gguf Qwen3 0.6B backbone, text -> tokens omnivoice-tokenizer-{variant}.gguf HuBERT + DAC + RVQ, tokens 24 kHz audio Set GGMLBACKEND to force a device, otherwise the runtime picks the best one available. Tokenizer GGUFs are not uniform quants. Three categories get a Same fallback as llama.cpp tensortypefallback: F16 has no block size and matches the runtime target dtype on every backend. The base LM (Qwen3 0.6B, hidden = 1024) has all dimensions divisible by 256 so the fallback never…
This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 256 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 256 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 256 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to have…
mms - vits pipelinetag: text-to-speech This repository contains the Hindi (hin) language text-to-speech (TTS) model checkpoint. This model is part of Facebook's Massively Multilingual Speech project, aiming to provide speech technology across a diverse range of languages. You can find more details about the supported languages and their ISO 639-3 codes in the MMS Language Coverage Overview, and see all MMS-TTS checkpoints on the Hugging Face Hub: facebook/mms-tts. MMS-TTS is available in the Transformers library from version 4.33 onwards. VITS (Variational Inference with adversarial learning for end-to-end Text-to-Speech) is an end-to-end speech synthesis model that predicts a speech…
Model · Video classification
VideoMAE model pre-trained for 1600 epochs in a self-supervised way and fine-tuned in a supervised way on Kinetics-400. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to…
Moirai, the Masked Encoder-based Universal Time Series Forecasting Transformer is a Large Time Series Model pre-trained on LOTSA data. For more details on the Moirai architecture, training, and results, please refer to the paper. Fig. 1: Overall architecture of Moirai. Visualized is a 3-variate time series, where variates 0 and 1 are target variables (i.e. to be forecasted, and variate 2 is a dynamic covariate (values in forecast horizon known). Based on a patch size of 64, each variate is patchified into 3 tokens. The patch embeddings along with sequence and variate id are fed into the Transformer. The shaded patches represent the forecast horizon to be forecasted, whose corresponding…
This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-large). The Moirai-1.1-R model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with…
This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 4017 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 4017 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 4017 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to…
TimeSformer model pre-trained on Kinetics-600. It was introduced in the paper TimeSformer: Is Space-Time Attention All You Need for Video Understanding? by Tong et al. and first released in this repository. Disclaimer: The team releasing TimeSformer did not write a model card for this model so this model card has been written by fcakyon. You can use the raw model for video classification into one of the 600 possible Kinetics-600 labels. Here is how to use this model to classify a video: For more code examples, we refer to the documentation.
TimeSformer model pre-trained on Kinetics-400. It was introduced in the paper TimeSformer: Is Space-Time Attention All You Need for Video Understanding? by Tong et al. and first released in this repository. Disclaimer: The team releasing TimeSformer did not write a model card for this model so this model card has been written by fcakyon. You can use the raw model for video classification into one of the 400 possible Kinetics-400 labels. Here is how to use this model to classify a video: For more code examples, we refer to the documentation.
VideoMAE model pre-trained on Kinetics-400 for 1600 epochs in a self-supervised way. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to the model as a sequence of…
Moirai, the Masked Encoder-based Universal Time Series Forecasting Transformer is a Large Time Series Model pre-trained on LOTSA data. For more details on the Moirai architecture, training, and results, please refer to the paper. Fig. 1: Overall architecture of Moirai. Visualized is a 3-variate time series, where variates 0 and 1 are target variables (i.e. to be forecasted, and variate 2 is a dynamic covariate (values in forecast horizon known). Based on a patch size of 64, each variate is patchified into 3 tokens. The patch embeddings along with sequence and variate id are fed into the Transformer. The shaded patches represent the forecast horizon to be forecasted, whose corresponding…
This checkpoint is a model fine-tuned for speech language identification (LID) and part of Facebook's Massive Multilingual Speech project. This checkpoint is based on the Wav2Vec2 architecture and classifies raw audio input to a probability distribution over 512 output classes (each class representing a language). The checkpoint consists of 1 billion parameters and has been fine-tuned from facebook/mms-1b on 512 languages. This MMS checkpoint can be used with Transformers to identify the spoken language of an audio. It can recognize the following 512 languages. Let's look at a simple example. First, we install transformers and some other libraries Note: In order to use MMS you need to have…
This is new updated version of Moirai-1.0-R (https://huggingface.co/Salesforce/moirai-1.0-R-base). The new Moirai model achieved significant improvements (~20%) for low-frequency cases like Yearly and Quarterly data in Normalised Mean Absolute Error (NMAE) for 40 datasets on the Monash repository. This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with…
This model has been pushed to the Hub using the PytorchModelHubMixin integration: This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use…
This model has been pushed to the Hub using the PytorchModelHubMixin integration: This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high-risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use…
VideoMAEv2-Base model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub. You can use the raw model for video feature extraction. Here is how to use this model to extract a video feature
Model · Video classification
This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 16 - evalbatchsize: 16 - lrschedulertype: linear - lrschedulerwarmupratio: 0.1 - trainingsteps: 348 - Transformers 4.49.0 - Pytorch 2.6.0+cu126 - Datasets 3.3.2 - Tokenizers 0.21.0
VideoMAEv2-Huge model pre-trained for 1200 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub. You can use the raw model for video feature extraction. Here is how to use this model to extract a video feature
Model · Video classification
VideoMAE model pre-trained for 2400 epochs in a self-supervised way and fine-tuned in a supervised way on Something-Something-v2. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are…
VideoMAEv2-Large model pre-trained for 800 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in GitHub. You can use the raw model for video feature extraction. Here is how to use this model to extract a video feature
Model · Video classification
VideoMAE model pre-trained for 1600 epochs in a self-supervised way and fine-tuned in a supervised way on Kinetics-400. It was introduced in the paper VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training by Tong et al. and first released in this repository. Disclaimer: The team releasing VideoMAE did not write a model card for this model so this model card has been written by the Hugging Face team. VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches. Videos are presented to…
Not without separate permission. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
By monthly downloads reported by the Hugging Face Hub: mms-300m-1130-forced-aligner (2.6M); jina-embeddings-v3 (2M); jina-reranker-v2-base-multilingual (1.1M).