You can deploy this model and start earning money today!

hasyarshad/
roman-urdu-translator

Name: roman-urdu-translator
Availability: InStock

Views

No views yet

English ↔ Roman Urdu

The trained weights for an 81M-parameter encoder–decoder transformer written from primitives in PyTorch — no nn.Transformer, no AutoModel, no training framework.

Roman Urdu is Urdu written in English letters, which is how Urdu is actually typed in messages. One model translates both directions and detects which one is wanted from the input.


Parameters	81M (`d_model` 512, 6+6 layers, 8 heads, `d_ff` 2048)
Vocabulary	24k joint byte-level BPE, shared by both languages
Corpus	1.81M sentence pairs, built for this project
Training	30 epochs; checkpoint chosen on validation loss
BLEU (Tatoeba, held out)	23.2 en→ur, 30.7 ur→en
Weights	fp16 on disk, fp32 at inference

Code: https://github.com/hasyarshad/roman-urdu-translator
Demo: https://haseeb-arshad.me/translator
Space: https://huggingface.co/spaces/hasyarshad/roman-urdu-translator

Use

bash

pip install torch tokenizers huggingface_hub
git clone https://github.com/hasyarshad/roman-urdu-translator.git
cd roman-urdu-translator
python -c "from huggingface_hub import snapshot_download; \
snapshot_download('hasyarshad/roman-urdu-translator', local_dir='export')"
python serve.py "wo larki pyari ha"

Files

File	What it is
`model.pt`	fp16 weights plus the config needed to rebuild the architecture
`tokenizer_joint.json`	the joint byte-level BPE tokenizer
`roman_urdu_map.json`	transliteration map, so Arabic-script input is romanised first
`export_info.json`	source checkpoint, epoch, validation loss, parameter count