MahtaFetrat
/

Homo-GE2PE-Persian

grapheme-to-phoneme

phoneme-translation

homograph-disambiguation

Model card Files Files and versions Community

MahtaFetrat commited on May 17

Commit

fdf2a9d

·

verified ·

1 Parent(s): 39a01b6

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ language:
 # Homo-GE2PE: Persian Grapheme-to-Phoneme Conversion with Homograph Disambiguation
-![Hugging Face](https://img.shields.io/badge/Hugging%20Face-Dataset-orange)
 **Homo-GE2PE** is a Persian grapheme-to-phoneme (G2P) model specialized in homograph disambiguation—words with identical spellings but context-dependent pronunciations (e.g., *مرد* pronounced as *mard* "man" or *mord* "died"). Introduced in *[Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models](link)*, the model extends **GE2PE** by fine-tuning it on the **HomoRich** dataset, explicitly designed for such pronunciation challenges.

 # Homo-GE2PE: Persian Grapheme-to-Phoneme Conversion with Homograph Disambiguation
+![Hugging Face](https://img.shields.io/badge/Hugging%20Face-Model-orange)
 **Homo-GE2PE** is a Persian grapheme-to-phoneme (G2P) model specialized in homograph disambiguation—words with identical spellings but context-dependent pronunciations (e.g., *مرد* pronounced as *mard* "man" or *mord* "died"). Introduced in *[Fast, Not Fancy: Rethinking G2P with Rich Data and Rule-Based Models](link)*, the model extends **GE2PE** by fine-tuning it on the **HomoRich** dataset, explicitly designed for such pronunciation challenges.