Downloads · 30 days
0
dimeshanthoney/mbart-large-m50-singlish-sinhala
mbart-large-m50-singlish-sinhala is a machine learning model from dimeshanthoney. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Fine-tuned mBART-50 for Singlish (Romanised Sinhala) → Sinhala script transliteration using a two-phase LoRA training strategy.
Downloads · 30 days
0
Access
Public
Updated Mar 8, 2026
Parameters
611M
2.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.4 GB · 99%
From the Hugging Face model README
Fine-tuned mBART-50 for Singlish (Romanised Sinhala) → Sinhala script transliteration using a two-phase LoRA training strategy.
| Phase | Dataset | Steps | LR |
|---|---|---|---|
| Phase 1 | Phonetic corpus (400,000 pairs) | 9,000 | 0.0003 |
| Phase 2 | Adhoc curated (10,000 × 10) | 4,000 | 6e-05 |
LoRA config: r=32, alpha=64, dropout 0.05
Target modules: q_proj, k_proj, v_proj, out_proj
| Metric | Phase 1 | Final |
|---|---|---|
| BLEU-char | 83.4084 | 83.7157 |
| WER | 0.2709 | 0.3266 |
| CER | 0.1002 | 0.0986 |
| ExactMatch | 0.1784 | 0.0932 |
from transformers import MBart50TokenizerFast, MBartForConditionalGeneration
repo = 'dimeshanthoney/mbart-large-m50-singlish-sinhala'
tokenizer = MBart50TokenizerFast.from_pretrained(repo)
model = MBartForConditionalGeneration.from_pretrained(repo)
src_text = 'oya kohomada'
tokenizer.src_lang = 'en_XX'
enc = tokenizer(src_text, return_tensors='pt')
gen = model.generate(
**enc,
forced_bos_token_id=tokenizer.lang_code_to_id['si_LK'],
max_length=128,
num_beams=5
)
print(tokenizer.batch_decode(gen, skip_special_tokens=True)[0])