|
--- |
|
pipeline_tag: translation |
|
language: |
|
- multilingual |
|
- en |
|
- am |
|
- ar |
|
- so |
|
- sw |
|
- pt |
|
- af |
|
- fr |
|
- zu |
|
- mg |
|
- ha |
|
- sn |
|
- arz |
|
- ny |
|
- ig |
|
- xh |
|
- yo |
|
- st |
|
- rw |
|
- tn |
|
- ti |
|
- ts |
|
- om |
|
- run |
|
- nso |
|
- ee |
|
- ln |
|
- tw |
|
- pcm |
|
- gaa |
|
- loz |
|
- lg |
|
- guw |
|
- bem |
|
- efi |
|
- lue |
|
- lua |
|
- toi |
|
- ve |
|
- tum |
|
- tll |
|
- iso |
|
- kqn |
|
- zne |
|
- umb |
|
- mos |
|
- tiv |
|
- lu |
|
- ff |
|
- kwy |
|
- bci |
|
- rnd |
|
- luo |
|
- wal |
|
- ss |
|
- lun |
|
- wo |
|
- nyk |
|
- kj |
|
- ki |
|
- fon |
|
- bm |
|
- cjk |
|
- din |
|
- dyu |
|
- kab |
|
- kam |
|
- kbp |
|
- kr |
|
- kmb |
|
- kg |
|
- nus |
|
- sg |
|
- taq |
|
- tzm |
|
- nqo |
|
|
|
license: apache-2.0 |
|
--- |
|
|
|
This is an improved version of [AfriCOMET-QE-STL (quality estimation single task)](https://github.com/masakhane-io/africomet) evaluation model: It receives a source sentence, and a translation, and returns a score that reflects the quality of the translation compared to the source. |
|
Different from the original AfriCOMET-QE-STL, this QE model is based on an improved African enhanced encoder, [afro-xlmr-large-76L](https://huggingface.co/Davlan/afro-xlmr-large-76L), which leads better performance on quality estimation of African-related machine translation, verified in WMT 2024 Metrics Shared Task. |
|
|
|
# Paper |
|
|
|
[AfriMTE and AfriCOMET: Empowering COMET to Embrace Under-resourced African Languages](https://arxiv.org/abs/2311.09828) (Wang et al., arXiv 2023) |
|
|
|
# License |
|
|
|
Apache-2.0 |
|
|
|
# Usage (AfriCOMET) |
|
|
|
Using this model requires unbabel-comet to be installed: |
|
|
|
```bash |
|
pip install --upgrade pip # ensures that pip is current |
|
pip install unbabel-comet |
|
``` |
|
|
|
Then you can use it through comet CLI: |
|
|
|
```bash |
|
comet-score -s {source-inputs}.txt -t {translation-outputs}.txt --model masakhane/africomet-qe-stl |
|
``` |
|
|
|
Or using Python: |
|
```python |
|
from comet import download_model, load_from_checkpoint |
|
|
|
model_path = download_model("masakhane/africomet-qe-stl") |
|
model = load_from_checkpoint(model_path) |
|
data = [ |
|
{ |
|
"src": "Nadal sàkọọ́lẹ̀ ìforígbárí o ní àmì méje sóódo pẹ̀lú ilẹ̀ Canada.", |
|
"mt": "Nadal's head to head record against the Canadian is 7–2.", |
|
}, |
|
{ |
|
"src": "Laipe yi o padanu si Raoniki ni ere Sisi Brisbeni.", |
|
"mt": "He recently lost against Raonic in the Brisbane Open.", |
|
} |
|
] |
|
model_output = model.predict(data, batch_size=8, gpus=1) |
|
print (model_output) |
|
``` |
|
|
|
# Intended uses |
|
|
|
Our model is intented to be used for **MT quality estimation**. |
|
|
|
Given a source sentence and a translation outputs a single score between 0 and 1 where 1 represents a perfect translation. |
|
|
|
|
|
|
