NVIDIA
NVIDIA
RIVA Punctuation and Capitalization for Brazilian Portuguese
Model
NVIDIA
NVIDIA
RIVA Punctuation and Capitalization for Brazilian Portuguese

For each word in the input text, the model: 1) predicts a punctuation mark that should follow the word (if any), the model supports commas, periods and question marks) and 2) predicts if the word should be capitalized or not.

This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Applications & Domains:Punctuation and Capitalization
Types:BERT-base
Intended Users:Data Scientists in Contact Center Transcription, Video Conferencing Transcription, Virtual Assistants, etc
Output:Text with Punctuations and capitalizations
Describe how the model works:Model adds Punctuations and Capitalizations to input text for the input language
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:Not applicable
Technical Limitations:Outputs may not be 100% accurate. Model can only capitalize first character of words
Verified to have met prescribed NVIDIA quality standards:Yes
Performance Metrics:Accuracy and F1 scores
Potential Known Risks:Not recommended for word-for-word/incomplete sentences as accuracy varies based on the context of input text
Licensing:https://developer.nvidia.com/riva/ga/license