Update README.md
Browse files
README.md
CHANGED
|
@@ -1 +1,18 @@
|
|
| 1 |
-
AI4Bharat's IndicBERT finetuned for few-shot transfer learning by fine-tuning on Hindi training data with Urdu validation and test sets. Expected low accuracy. Leverages mbert's tokenizer in this implementation.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
AI4Bharat's IndicBERT finetuned for few-shot transfer learning by fine-tuning on Hindi training data with Urdu validation and test sets. Expected low accuracy. Leverages mbert's tokenizer in this implementation.
|
| 2 |
+
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
language:
|
| 6 |
+
- ru
|
| 7 |
+
- en
|
| 8 |
+
tags:
|
| 9 |
+
- translation
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- wmt19
|
| 13 |
+
metrics:
|
| 14 |
+
- f1
|
| 15 |
+
- recall
|
| 16 |
+
- accuracy
|
| 17 |
+
|
| 18 |
+
---
|