Dear followers, this is a quick note to let you know that from now on, I will also be posting on Substack. If you’d like, you can follow me there. Julien's Newsletter AI and Machine Learning. Click to read Julien's Newsletter, by Julien Simon 🇺🇦, a Substack publication. Launched 37…julsimon.substack.com For those of you who prefer to use Medium, no worries! I will definitely keep publishing here as well :)

Transformer models deliver state-of-the-art performance on a wide range of machine learning tasks, such as natural language processing, computer vision, speech, and more. However, training them at scale often requires a large amount of computing power, making the whole process unnecessarily long, complex, and costly. Join us for a live webinar to learn how the Hugging Face and Habana Labs joint solution makes it easier and quicker to train high-quality transformer models. Live demo included!

In this video, I show how to use fine-tune a state of the art Conformer model for audio keyword classification, and build a Gradio Space to showcase it. I also quickly test the model with distorted audio to see how resilient it it. Dataset: https://huggingface.co/datasets/speech_commands Base model: https://huggingface.co/facebook/wav2vec2-conformer-rel-pos-large Fine-tuned model: https://huggingface.co/juliensimon/wav2vec2-conformer-rel-pos-large-finetuned-speech-commands

My session for Analytics Vidhya’s Data Hour is now online. Get ready for a 1-hour grand tour of Hugging Face: preparing data with datasets, training and predicting with transformers, sharing on the hub, deploying with the Inference API, building a web app with Spaces, and quantizing with Optimum. My most complete session yet. Enjoy :)

In this video, I show how to use MLflow with the Transformers library, and why it’s a good idea to store the logs on the Hugging Face hub :) Let us know how you’d like to use MLflow with Transformers and the Hugging Face hub! Please join the discussion at https://discuss.huggingface.co/t/calling-mlflow-users/20420 Doc: https://huggingface.co/docs/transformers/v4.20.1/en/main_classes/callback#transformers.integrations.MLflowCallback

Training Transformers on tabular data is quickly becoming a thing. That’s all the excuse I needed to look at the new TabTransformer algo in Amazon SageMaker, and sneak around a bit to learn what it’s actually built with.

In this session, we’ll introduce you to Transformer models and what business problems you can solve with them. Then, we’ll show you how you can simplify and accelerate your machine learning projects end-to-end: experimenting, training, optimizing, and deploying. Along the way, we’ll run some demos to keep things concrete and exciting! New to Transformers? https://huggingface.co/tasks https://huggingface.co/course