A transformer model based on the SONAR architecture that performs token classification to restore punctuation and capitalization across multiple languages. It is particularly useful for processing ASR output, normalizing informal text, or preparing data for downstream NLP tasks. The model is distributed via the Transformers library.
Fullstop Punctuation Multilingual Sonar Base is an Other AI project. Automatically adding proper punctuation and capitalization to unpunctuated multilingual text. It is built as an open-source project for developers. The project is open source (Open Source). It runs on the web, the command line, and API.
oliverguhr builds and maintains Fullstop Punctuation Multilingual Sonar Base, and it first shipped in 2022. Among its 3 catalogued features are punctuation restoration, capitalization, and multilingual support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match