---
language:
- dv
tags:
- transliteration
- dhivehi
- thaana
- byt5
- news
- nlp
license: apache-2.0
base_model: google/byt5-small
datasets:
- alakxender/dhivehi-transliteration-pairs
widget:
- text: "ރައީސް މުއިއްޒު ވަޑައިގެންފި"
  example_title: "Presidential Visit"
- text: "ސީރިއާގެ ކަންކަމުގެ ތެރެއަށް އިސްރާއީލް ނުވަނުމަށް"
  example_title: "Global Politics (Syria)"
- text: "އެންމެ މުހިންމީ ކުޅިވަރު ދާއިރާ ހިންގާނެ މީހުން އުފެއްދުން"
  example_title: "Sports (General)"
inference:
  parameters:
    max_length: 256
---

# Dhivehi ByT5 News Transliteration (v1)

This model is a specialized **Thaana-to-Latin transliteration model** optimized for Maldivian news media. 

It is designed to handle the complexities of journalistic text, focusing on the correct preservation of **context, English loan words, and named entities** (e.g., Country names, Acronyms like UN, Sports teams).

## 🧠 Training Strategy

1.  **Base Model:** [google/byt5-small](https://huggingface.co/google/byt5-small)
2.  **General Fine-tuning:** Tuned on the [alakxender/dhivehi-transliteration-pairs](https://huggingface.co/datasets/alakxender/dhivehi-transliteration-pairs) dataset (~180k pairs) to learn general transliteration rules.
3.  **Domain Adaptation:** Further fine-tuned on a high-quality dataset of 10k News headlines to capture journalistic style and entities.
## 📊 Performance Samples

| Category | Thaana Input | Model Output |
| :--- | :--- | :--- |
| **Global Politics** | ސީރިއާގެ ކަންކަމުގެ ތެރެއަށް އިސްރާއީލް ނުވަނުމަށް | `Syria ge kankamuge thereah Israel nuvanumah` |
| **Acronyms** | ރާއްޖޭގެ ރެކޯޑުތައް އދ އިން ބަލަނީ | `Raajjeyge record thah UN in balanee` |
| **English Loan Words** | ސްކޭމާއި ދެކޮޅަށް ހިންގި ޚާއްސަ އޮޕަރޭޝަނެއް | `Scam aai dhekolhah hingi khaassa operation eh` |
| **Sports** | ވެސްޓް ހޭމް އަތުން ޗެލްސީ އަށް މޮޅެއް | `West Ham athun Chelsea ah molheh` |
| **Dates** | އޮކްޓޯބަރ 3 ގެ މުޒާހަރާ | `October 3 ge muzaaharaa` |

## 💻 Usage

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Neobe/dhivehi-byt5-thaana2latin-v1")
model = AutoModelForSeq2SeqLM.from_pretrained("Neobe/dhivehi-byt5-thaana2latin-v1")

text = "ސީރިއާގެ ކަންކަމުގެ ތެރެއަށް އިސްރާއީލް ނުވަނުމަށް ޓްރަމްޕް ގޮވާލައްވައިފި"
inputs = tokenizer(text, return_tensors="pt")

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

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
# Output: Syria ge kankamuge thereah Israel nuvanumah Trump govaalavvaifi