About Microsoft
Explore research at Microsoft, a site featuring the impact of research along with publications, products, downloads, and research careers.
Microsoft Research conducts fundamental science and technology research across a spectrum of research areas. With labs around the globe we pursue breakthroughs across the computing and AI stack to accelerate discovery across sciences and advance the frontiers of computing and AI to create new foundations for others to build upon.
Artificial intelligence | Search & information retrieval | Human language technologies | Human-computer interaction | Computer vision | Graphics & multimedia | Audio & acoustics
Medical, health & genomics | Economics | Social sciences | Technology for emerging markets | Ecology & environment
Website ↗Documentation ↗
Source ↗ · 2026-11-12T02:17:04.301031227ZazureFoundry/HuggingFace/microsoft-tapex-large-finetuned-wtq@4
# TAPEX (large-sized model) TAPEX was proposed in [TAPEX: Table Pre-training via Learning a Neural SQL Executor](https://arxiv.org/abs/2107.07653) by Qian Liu, Bei Chen, Jiaqi Guo, Morteza Ziyadi, Zeqi Lin, Weizhu Chen, Jian-Guang Lou. The original repo can be found [here](htt
huggingface/microsoft/TRELLIS.2-4B
huggingface/microsoft/TRELLIS-image-large
azureFoundry/HuggingFace/microsoft-unispeech-sat-base-100h-libri-ft@1
# UniSpeech-SAT-Base-Finetuned-100h-Libri [Microsoft's UniSpeech](https://www.microsoft.com/en-us/research/publication/unispeech-unified-speech-representation-learning-with-labeled-and-unlabeled-data/) A [unispeech-sat-base model]( ) that was fine-tuned on 100h hours of Libris
- Input modalities
- audio
- Output modalities
- text
- Capabilities
- audioInput
Benchmarks
azureFoundry/HuggingFace/microsoft-unixcoder-base@1
# Model Card for UniXcoder-base # Model Details ## Model Description UniXcoder is a unified cross-modal pre-trained model that leverages multimodal data (i.e. code comment and AST) to pretrain code representation. - **Developed by:** Microsoft Team - **Shared by [Opti
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
azureFoundry/HuggingFace/microsoft-unixcoder-base-nine@1
# Model Card for UniXcoder-base # Model Details ## Model Description UniXcoder is a unified cross-modal pre-trained model that leverages multimodal data (i.e. code comment and AST) to pretrain code representation. - **Developed by:** Microsoft Team - **Shared by [Opti
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
vertexAI/publishers/hf-microsoft/models/userlm-8b@001
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-vibevoice-asr-hf@2
## VibeVoice-ASR (Transformers-compatible version) [](https://github.com/microsoft/VibeVoice) [](https://aka.ms/vibevoice-asr)
Benchmarks
- Open ASR Leaderboard: 2.02%
vertexAI/publishers/hf-microsoft/models/wavecoder-ds-6.7b@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-microsoft/models/wavecoder-ultra-6.7b@001
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-wavlm-base@1
# WavLM-Base [Microsoft's WavLM](https://github.com/microsoft/unilm/tree/master/wavlm) The base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
Benchmarks
azureFoundry/HuggingFace/microsoft-wavlm-base-plus@1
# WavLM-Base-Plus [Microsoft's WavLM](https://github.com/microsoft/unilm/tree/master/wavlm) The base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenize
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
Benchmarks
huggingface/microsoft/wavlm-large
- Capabilities
- embeddings
Benchmarks
huggingface/microsoft/WizardLM-2-7B
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 63.66%
azureFoundry/HuggingFace/microsoft-xdoc-base-squad2-0@1
# XDoc ## Introduction XDoc is a unified pre-trained model that deals with different document formats in a single model. With only 36.7% parameters, XDoc achieves comparable or better performance on downstream tasks, which is cost-effective for real-world deployment. [XDoc: Un
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/microsoft-xlm-align-base@3
# XLM-Align **XLM-Align** (ACL 2021, [paper](https://aclanthology.org/2021.acl-long.265/), [repo](https://github.com/CZWin32768/XLM-Align), [model](https://huggingface.co/microsoft/xlm-align-base)) Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignmen
azureFoundry/HuggingFace/microsoft-xtremedistil-l12-h384-uncased@5
`microsoft/xtremedistil-l12-h384-uncased` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-classification` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, lim
azureFoundry/HuggingFace/microsoft-xtremedistil-l6-h256-uncased@7
`microsoft/xtremedistil-l6-h256-uncased` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-classification` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limi