You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Code and Resources for "LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study", introducing methods to leverage LLMs for G2P tasks without additional training, featuring Sentence-Bench and Kaamel-Dict.
In this repository, we provide a neural model based on BERT and BiLSTM neural networks, which can recognize the Kasreh Ezafeh (Genitive Conjunction /e/) in a Persian sentence or text.
In this repository, we provide a joint neural model based on BERT and two BiLSTM neural networks, which can jointly recognize the Kasreh Ezafeh (Genitive Conjunction /e/) and Comma in a Persian sentence or text.