GPU-optimized AI, Machine Learning, & HPC Software

NVIDIA

STT Multilingual FastConformer Hybrid Transducer-CTC Large P&C

The large version (114M) of the Multilingual speech recognition model with a FastConformer encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 2560 and emits text with punctuation and capitalization.

Model

NVIDIA

STT European FastConformer Hybrid Transducer-CTC Large P&C

English / Spanish / French / German speech recognition model with a FastConformer large (114M) encoder and a Hybrid decoder (joint RNNT-CTC loss). The model has a vocab size of 2560 and emits text with punctuation and capitalization.

Model

NVIDIA

RIVA Citrinet ASR French

French Citrinet ASR model trained on RIVA ASR set

Model

NVIDIA

Riva ASR French LM

Base French 4-gram LM

Model

NVIDIA

RIVA ASR French LM

Base French n-gram LM

Model

NVIDIA

NemoCurator Multilingual Domain Classifier

A text classification model to classify documents into one of 26 domain classes across 52 languages.

Model

NVIDIA

RIVA Punctuation and Capitalization for French

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, hyphens and question marks) and 2) predicts if the word should be capitalized or not.

Model