Introducing Our New Punctuation Restoration and Truecasing Models

We’ve trained new Punctuation and Truecasing models on 13 billion words to achieve a 39% F1 score improvement for mixed-case words. Building on a novel application of a hybrid architecture for a character-level classifier reduces inference time and improves the scalability of our Speech AI systems.

ai systems announcements application architecture billion building case classifier hybrid improvement inference mixed novel scalability speech speech ai systems words