
Build Language Models with Python
Build Real NLP Tools for Spam Detection and Sentiment AnalysisBy Esther FontaineLength7h 30m
About this audiobook
natural language processing with Python and transformers for beginners. Master natural language processing and transformer models with this hands-on guide. From tokenization and embeddings to fine-tuning for classification, search, and chat, Esther Fontaine delivers a practical, code-first approach using Python. Whether you're a beginner or a pro, you'll build real-world language models step by step. This book stands out from Wallace and Ali by focusing on applied Python and transformers, not theory or investing. Learn to preprocess text, train BERT, deploy chatbots, and optimize performance—all with clear examples and ready-to-run code. Ideal for data scientists, ML engineers, and anyone eager to create AI that understands language.
Discover how to: tokenize and embed text with Hugging Face, fine-tune pre-trained models for sentiment analysis and search, build a custom chat system with GPT-like architectures, and scale your models for production. Each chapter includes exercises and real datasets to cement your skills. With Esther Fontaine's guidance, you'll go from zero to building production-ready NLP systems. Unlike abstract discussions in other books, this is a straight-to-code manual that gets results. Compare with Louis and Huyen—this is the practical Python path to NLP mastery.
This hands-on AI/ML/Data guide is written to be used at the keyboard: every concept is paired with something you can run, adapt, and keep. You move from first principles to real, working results, with the common errors and fixes called out along the way so you are never stuck for long.
Audiobook details
GenreTechnology
Length7 hrs 30 mins
Narrated byListen with 1,000+ voices
FormateBook with Audio
LanguageEnglish
Table of contents
1Introduction
4Chapter 2 — Cleaning Real-World Text (pt. 1)
2Preface
5Chapter 2 — Cleaning Real-World Text (pt. 2)
3Chapter 1 — What NLP Can Do for You
6Chapter 2 — Cleaning Real-World Text (pt. 3)