Update app.py
Browse files
app.py
CHANGED
|
@@ -51,7 +51,7 @@ Since the Axolotl corpus contains misaligments, we just select the best samples
|
|
| 51 |
| Una tortillita nom谩s - Se taxkaltsin saj |
|
| 52 |
| Vida econ贸mica de Tenochtitlan |
|
| 53 |
|
| 54 |
-
Also, to increase the amount of data we collected 3,000 extra samples from the web.
|
| 55 |
|
| 56 |
### Model and training
|
| 57 |
We employ two training-stages using a multilingual T5-small. This model was chosen because it can handle different vocabularies and suffixes. T5-small is pretrained on different tasks and languages (French, Romanian, English, German).
|
|
|
|
| 51 |
| Una tortillita nom谩s - Se taxkaltsin saj |
|
| 52 |
| Vida econ贸mica de Tenochtitlan |
|
| 53 |
|
| 54 |
+
Also, to increase the amount of data, we collected 3,000 extra samples from the web.
|
| 55 |
|
| 56 |
### Model and training
|
| 57 |
We employ two training-stages using a multilingual T5-small. This model was chosen because it can handle different vocabularies and suffixes. T5-small is pretrained on different tasks and languages (French, Romanian, English, German).
|