# Text normalization

Turkish grammar correction model fine-tuned based on mbart-large-50

Distilled model based on FRED-T5-1.7B architecture for automatic correction of Russian spelling, punctuation, and capitalization errors

A sequence-to-sequence model supporting English automatic speech recognition (ASR), capable of outputting normalized text, timestamp annotations, and multi-speaker segmentation.

A compound word normalization model for decomposing and normalizing compound words, enhancing language models' ability to process compound words.

A Bengali pre-trained model based on the sequence-to-sequence Transformer architecture, optimized for natural language generation tasks

BanglaT5 is a Bengali sequence-to-sequence transformer model pre-trained with Span Corruption objectives, achieving state-of-the-art performance in multiple Bengali natural language generation tasks.

A model based on bert-base-uncased architecture, fine-tuned for punctuation restoration on the Yelp review dataset, capable of predicting punctuation and capitalization restoration for lowercase text.