magistermilitum
commited on
Commit
•
dd45bb1
1
Parent(s):
f17825a
Update README.md
Browse files
README.md
CHANGED
@@ -17,9 +17,21 @@ language:
|
|
17 |
|
18 |
## Model Details
|
19 |
|
20 |
-
This is a Fine-tuned version of the multilingual
|
21 |
-
in a Flat and nested manner. The train dataset entails 8k annotated texts on medieval latin, french and Spanish from a period ranging from 11th to 15th centuries.
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
-
### How to Get Started with the Model
|
25 |
-
The model is intended to be used in a simple way manner:
|
|
|
17 |
|
18 |
## Model Details
|
19 |
|
20 |
+
This is a Fine-tuned version of the multilingual Bert model on medieval texts. The model is intended to be used as a fondation for other ML tasks on NLP and HTR environments.
|
|
|
21 |
|
22 |
+
The train dataset entails 650M of tokens coming from texts on classical and medieval latin; old french and old Spanish from a period ranging from 5th BC to 16th centuries.
|
23 |
+
|
24 |
+
Several big corpora were cleaned ans transformed to be used during the process training:
|
25 |
+
|
26 |
+
| dataset | size | Lang |
|
27 |
+
| ------------- |:-------------:| -----:|
|
28 |
+
| CC100 | 3,2Gb | la |
|
29 |
+
| Corpus Corporum | 3,0Gb | la |
|
30 |
+
| CEMA | 320Mb | la+fro |
|
31 |
+
| HOME | 38Mb | la+fro |
|
32 |
+
| BFM | 34Mb | fro |
|
33 |
+
| AND | 19Mb | fro |
|
34 |
+
| CODEA | 13Mb | spa |
|
35 |
+
| | ~6,5Gb | |
|
36 |
+
| | 650M tk (4,5Gb) | |
|
37 |
|
|
|
|