Neobe/dhivehi-byt5-latin2thaana-v1

Dhivehi ByT5 Latin to Thaana (v1)

This model is a specialized Latin-to-Thaana transliteration model optimized for Maldives news media, but also capable of handling both formal journalistic text and casual social media typing.

It functions as a "Hybrid" model: it respects the casual spacing of chat messages while correctly applying formal grammatical rules (such as compounding verbs) when it detects a news context.

🧠 Training Strategy

1. 1.Base Model: google/byt5-small
2. 2.General Fine-tuning: Tuned on the alakxender/dhivehi-transliteration-pairs dataset (~150k pairs) to learn general phonetics and spelling.
3. 3.Domain Adaptation: Further fine-tuned on a high-quality dataset of 10k News headlines to recognize formal entities and apply correct grammatical spacing for official terms.

📊 Performance Samples

💻 Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Neobe/dhivehi-byt5-latin2thaana-v1")
model = AutoModelForSeq2SeqLM.from_pretrained("Neobe/dhivehi-byt5-latin2thaana-v1")

text = "Raeesul jumhooriyya miadhu ganoonu thasdheegu kuravvaifi"
inputs = tokenizer(text, return_tensors="pt")

outputs = model.generate(**inputs, max_length=256)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
# Output: ރައީސުލް ޖުމްހޫރިއްޔާ މިއަދު ގާނޫނު ތަސްދީގުކުރައްވައިފި