|
--- |
|
language: |
|
- ur |
|
- en |
|
license: apache-2.0 |
|
datasets: |
|
- iwslt14 |
|
metrics: |
|
- bleu |
|
library_name: fairseq |
|
pipeline_tag: translation |
|
--- |
|
|
|
### English to Urdu Translation |
|
Urdu to English translation model is a Transformer model trained on IWSLT back-translated data using Faireq. |
|
This model is produced during the experimentation related to building Context-Aware NMT models for low-resourced languages such as Urdu, Hindi, Sindhi, Pashtu and Punjabi. This particular model does not contains any contextual information and it is baseline sentence-level transformer model. |
|
The evaluation is done on WMT2017 standard test set. |
|
|
|
* source group: Urdu |
|
* target group: English |
|
|
|
* model: transformer |
|
* Contextual |
|
* Test Set: WMT2017 |
|
* pre-processing: Moses + Indic Tokenizer |
|
* Dataset + Libray Details: [DLNMT](https://github.com/sami-haq99/nrpu-dlnmt) |
|
|
|
## Benchmarks |
|
|
|
| testset | BLEU | |
|
|-----------------------|-------| |
|
| Wmt2017 | 57.95 | |
|
|
