Commit
·
dde3164
1
Parent(s):
2e172b5
readme updated
Browse files
README.md
CHANGED
|
@@ -1,8 +1,12 @@
|
|
| 1 |
# Multilingual_Language_Detection
|
| 2 |
|
| 3 |
-
This model is a fine-tuned version of [
|
|
|
|
| 4 |
It achieves the following results on the evaluation set:
|
| 5 |
-
- Loss:
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
## Languages
|
| 8 |
|
|
@@ -11,3 +15,10 @@ It's trained in more than 22 different languages, they are listed below.
|
|
| 11 |
Arabic, Urdu, Tamil, Hindi, English, French, Spanish, Japanese, Chinese, Thai, Indonesian, Dutch, Korean, Latin, Persian, Portugese,
|
| 12 |
Pushto, Romanian, Russian, Swedish, Turkish, Estonian
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Multilingual_Language_Detection
|
| 2 |
|
| 3 |
+
This model is a fine-tuned version of [XLM-Roberta-base](https://huggingface.co/bert-base-uncased) on the multilingual dataset.
|
| 4 |
+
|
| 5 |
It achieves the following results on the evaluation set:
|
| 6 |
+
- Training Loss : 0.087900
|
| 7 |
+
- Validation Loss : 0.067496
|
| 8 |
+
- Accuracy : 0.988409
|
| 9 |
+
- F1 : 0.988507
|
| 10 |
|
| 11 |
## Languages
|
| 12 |
|
|
|
|
| 15 |
Arabic, Urdu, Tamil, Hindi, English, French, Spanish, Japanese, Chinese, Thai, Indonesian, Dutch, Korean, Latin, Persian, Portugese,
|
| 16 |
Pushto, Romanian, Russian, Swedish, Turkish, Estonian
|
| 17 |
|
| 18 |
+
## Training result
|
| 19 |
+
|
| 20 |
+
Epoch Training_Loss Validation_Loss Accuracy F1
|
| 21 |
+
1 0.003000 0.083116 0.986136 0.986332
|
| 22 |
+
2 0.000900 0.069443 0.987273 0.987403
|
| 23 |
+
3 0.087900 0.067496 0.988409 0.988507
|
| 24 |
+
|