Create powerful AI models without code

A new way to automatically train, evaluate and deploy state-of-the-art NLP models.

Watch trailer

NLP made simple

Train custom machine learning models by simply uploading data.

Automatic training

AutoNLP will find the best models for your data automatically.

Fast deployment

Your models are available on the Hugging Face Hub, and ready to serve.

Customer stories

AutoNLP is the first AutoML tool we have used that can compete with a dedicated ML Engineer. This allows us to spend our time on research and improving data filters/generation, which is game-changing for a small team like ours. The integration with the HuggingFace ecosystem is great, and adds a lot of value even if you host the models yourself.
Sam Havens
Director of NLP Engineering, Writer
HuggingFace's AutoNLP tool chain is a step forward towards Democratizing NLP. It offers non-researchers like me the ability to train highly performant NLP models and get them deployed at scale, quickly and efficiently.
Kumaresan Manickavelu
NLP Product Manager, eBay
AutoNLP has provided us with zero to hero model in minutes with no experience required.
Ben Nimmo
Founder & CTO, Orlo

How does it work?

Create a new project

Choose a task and you're ready to go!

Create a new autonlp project

Upload your data

We support csv and json file formats

Upload your data to AutoNLP

Start auto-trainings

AutoNLP automatically finds the best models for your data

AutoNLP automatically finds the best models for your data

Track models progress

Monitor and track models performance

Monitor and track models performance

Use your models

With dedicated HTTP endpoints or from the CLI

autonlp predict --project sentiment_detection --model_id 42 --sentence "i love autonlp"


What is AutoNLP?
AutoNLP is an automatic way to train and deploy state-of-the-art NLP models, seamlessly integrated with the Hugging Face ecosystem.
What NLP tasks are available for training?
Available today: binary classification, multi-class classification, regression, entity recognition, summarization, and automatic speech recognition.
Which model languages are available?
Available today: English, German, French, Spanish, Finnish, Swedish, Hindi, Dutch and more! Check out all supported languages in the documentation.
How is my training data secure?
Your training data stays on our server, and is private to your account. All data transfers are SSL-protected.
How much does it cost?
Based on how much training data and model variants are created, we send you a compute cost and payment link - as low as $10 per job.
What training data formats are supported?
CSV, TSV or JSON files, hosted anywhere. We delete your training data after training is done.