Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Project Overview: Bengali Text Correction
|
| 2 |
|
| 3 |
The goal of this project was to develop a software model that could fix grammatical and syntax errors in Bengali text. The approach was similar to how a language translator works, where the incorrect sentence is transformed into a correct one. We fine tune a pertained model, namely [mBart50] with a [dataset] of 1.M samples for 6500 steps and achieve a result of 0.44 bleu Score.
|
|
@@ -77,4 +86,4 @@ I'm also planning to run a 4-bit quantization on the same model to see how it pe
|
|
| 77 |
|
| 78 |
## Resources and References:
|
| 79 |
[Dataset Source](https://github.com/hishab-nlp/BNSECData)
|
| 80 |
-
[Model Documentation and Troubleshooting](https://huggingface.co/docs/transformers/model_doc/mbart)
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- bn
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
+
library_name: transformers
|
| 8 |
+
pipeline_tag: text2text-generation
|
| 9 |
+
---
|
| 10 |
# Project Overview: Bengali Text Correction
|
| 11 |
|
| 12 |
The goal of this project was to develop a software model that could fix grammatical and syntax errors in Bengali text. The approach was similar to how a language translator works, where the incorrect sentence is transformed into a correct one. We fine tune a pertained model, namely [mBart50] with a [dataset] of 1.M samples for 6500 steps and achieve a result of 0.44 bleu Score.
|
|
|
|
| 86 |
|
| 87 |
## Resources and References:
|
| 88 |
[Dataset Source](https://github.com/hishab-nlp/BNSECData)
|
| 89 |
+
[Model Documentation and Troubleshooting](https://huggingface.co/docs/transformers/model_doc/mbart)
|