AI Workshop: Building AI Applications with Hugging Face Models
34mIntermediate2025-04-02
Authors

Dhhyey Desai
Google-Certified Python Expert, Microsoft-Certified Instructor
Course details
This course is designed to equip you with the skills required to develop AI applications using cutting-edge models from Hugging Face. Throughout the course, instructor Dhhyey Desai outlines three hands-on projects: sentiment analysis in multiple languages using the Aya 23 model, object detection in images with the LLaVA model, and automatic speech recognition using wav2vec 2.0. Each chapter guides you through the essential steps of setting up your environment, preprocessing data, implementing the models, and visualizing or post-processing the results. By the end of this course, you'll have practical experience deploying AI solutions across various domains and a solid understanding of how to leverage Hugging Face's powerful APIs.
Learning objectives
Learn the capabilities of Aya 23, LLaVA, and wav2vec 2.0 models.
Implement AI applications for sentiment analysis, object detection, and speech recognition.
Prepare text, image, and audio data for use with Hugging Face models.
Load, implement, and assess the performance of different AI models.
Learning objectives
Learn the capabilities of Aya 23, LLaVA, and wav2vec 2.0 models.
Implement AI applications for sentiment analysis, object detection, and speech recognition.
Prepare text, image, and audio data for use with Hugging Face models.
Load, implement, and assess the performance of different AI models.
Skills covered
Hugging FaceProgramming FoundationsMachine LearningArtificial Intelligence FoundationsArtificial Intelligence (AI)Software DevelopmentOne-Off
Concepts
0. Introduction
- 01 - Get hands on with AI and Hugging Face models
- 02 - What you should know
1. Multilingual Sentiment Analysis with Aya
- 03 - What is Aya
- 04 - Processing text data
- 05 - Implementing sentiment analysis
2. Object Detection with LLaVA
- 06 - What is LLaVA
- 07 - Preparing data
- 08 - Building the model
3. Automatic Speech Recognition with wav2vec
- 09 - What is wav2vec
- 10 - Constructing the foundational model
- 11 - Obtaining logits
- 12 - Post-processing and transcription
Conclusion
- 13 - What's next