saudaloufi12
commited on
Commit
•
53bbcda
1
Parent(s):
4d17e32
saud12
Browse files
README.md
CHANGED
@@ -1,8 +1,27 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
|
8 |
---
|
|
|
1 |
+
from datasets import Dataset
|
2 |
+
|
3 |
+
# Prepare your data
|
4 |
+
data = [
|
5 |
+
{"source_text": "Hello, how are you?", "target_text": "مرحبا كيف حالك؟"},
|
6 |
+
{"source_text": "I am fine, thank you.", "target_text": "أنا بخHere's the complete code to prepare and upload a translation dataset to Hugging Face using the `datasets` library:
|
7 |
+
|
8 |
+
```python
|
9 |
+
from datasets import Dataset
|
10 |
+
|
11 |
+
# Prepare your data
|
12 |
+
data = [
|
13 |
+
{"source_text": "Hello, how are you?", "target_text": "مرحبا كيف حالك؟"},
|
14 |
+
{"source_text": "I am fine, thank you.", "target_text": "أنا بخير، شكراً لك."},
|
15 |
+
{"source_text": "What is your name?", "target_text": "ما هو اسمك؟"},
|
16 |
+
...
|
17 |
+
]
|
18 |
+
|
19 |
+
# Convert your data into a format compatible with Hugging Face
|
20 |
+
dataset = Dataset.from_dict(data)
|
21 |
+
dataset = dataset.rename_column("source_text", "input_text")
|
22 |
+
dataset = dataset.rename_column("target_text", "target_text")
|
23 |
+
|
24 |
+
# Upload your data to Hugging Face
|
25 |
+
dataset.save_to_disk("translation_dataset")
|
26 |
|
27 |
---
|