Update README
Browse files
README.md
CHANGED
|
@@ -7,7 +7,23 @@ pipeline_tag: translation
|
|
| 7 |
## Model Details
|
| 8 |
|
| 9 |
- **Pre-trained Model**: Rogendo/sw-en
|
| 10 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
- **Corpus Name**: WikiMatrix
|
| 13 |
- **Package**: WikiMatrix.en-sw in Moses format
|
|
|
|
| 7 |
## Model Details
|
| 8 |
|
| 9 |
- **Pre-trained Model**: Rogendo/sw-en
|
| 10 |
+
- ## Model Details
|
| 11 |
+
|
| 12 |
+
- Transformer architecture used
|
| 13 |
+
- Trained on a 210000 corpus pairs
|
| 14 |
+
- Pre-trained Helsinki-NLP/opus-mt-en-swc
|
| 15 |
+
- 2 models to enforce biderectional translation
|
| 16 |
+
### Model Description
|
| 17 |
+
|
| 18 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
- **Developed by:** Peter Rogendo, Frederick Kioko
|
| 23 |
+
- **Model type:** Transformer
|
| 24 |
+
- **Language(s) (NLP):** Transformer, Pandas, Numpy
|
| 25 |
+
- **License:** Distributed under the MIT License
|
| 26 |
+
- **Finetuned from model [Helsinki-NLP/opus-mt-en-swc]:** [This pre-trained model was re-trained on a swahili-english sentence pairs that were collected across Kenya. Swahili is the national language and is among the top three of the most spoken language in Africa. The sentences that were used to train this model were 210000 in total.]
|
| 27 |
|
| 28 |
- **Corpus Name**: WikiMatrix
|
| 29 |
- **Package**: WikiMatrix.en-sw in Moses format
|