Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,48 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
---
|
4 |
+
---
|
5 |
+
license: mit
|
6 |
+
datasets: Hemanth-thunder/en_ta
|
7 |
+
language:
|
8 |
+
- ta
|
9 |
+
- en
|
10 |
+
widget:
|
11 |
+
- text: Actor Vijay is competing an 2026 election.
|
12 |
+
- text: you have to study well for exams
|
13 |
+
- text: The Sun is approximately 4.6 billion years older than Earth.
|
14 |
+
pipeline_tag: text2text-generation
|
15 |
+
---
|
16 |
+
|
17 |
+
## Model Details
|
18 |
+
- **Model Name**: English-Tamil-Translator
|
19 |
+
- **Model Type**: Deep Learning Model
|
20 |
+
- **Language**: Python
|
21 |
+
- **Task**: Language Translation
|
22 |
+
|
23 |
+
## How to Use
|
24 |
+
1. **Install Gemma Python Package**:
|
25 |
+
```bash
|
26 |
+
pip install -q -U transformers==4.38.0
|
27 |
+
```
|
28 |
+
|
29 |
+
## Inference
|
30 |
+
1. **How to use the model in our notebook**:
|
31 |
+
```python
|
32 |
+
# Load model directly
|
33 |
+
import torch
|
34 |
+
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
35 |
+
|
36 |
+
checkpoint = "Mr-Vicky-01/English-Tamil-Translator"
|
37 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
38 |
+
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
|
39 |
+
|
40 |
+
def language_translator(text):
|
41 |
+
tokenized = tokenizer([text], return_tensors='pt')
|
42 |
+
out = model.generate(**tokenized, max_length=128)
|
43 |
+
return tokenizer.decode(out[0],skip_special_tokens=True)
|
44 |
+
|
45 |
+
text_to_translate = "i have to play football now!"
|
46 |
+
output = language_translator(text_to_translate)
|
47 |
+
print(output)
|
48 |
+
```
|