WWDC23 · 14 min · AI & Machine Learning

Explore Natural Language multilingual models

Learn how to create custom Natural Language models for text classification and word tagging using multilingual, transformer-based embeddings. We’ll show you how to train with less data and support up to 27 different languages across three scripts. Find out how to use these embeddings to fine-tune complex models trained in PyTorch and TensorFlow. For more on Natural Language, check out "Make apps smarter with Natural Language” from WWDC20.

Transcript ↓ .srt ↓ .txt all transcripts