Translation
Transformers
ONNX
Nepali
English
setu_translation
feature-extraction
nepali
english
multilingual
code-mixed
romanized
devanagari
custom_code
Eval Results (legacy)
Instructions to use santoshdahal/setu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use santoshdahal/setu with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("translation", model="santoshdahal/setu", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("santoshdahal/setu", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -14,11 +14,11 @@ tags:
|
|
| 14 |
- onnx
|
| 15 |
pipeline_tag: translation
|
| 16 |
widget:
|
| 17 |
-
- text: "mero
|
| 18 |
example_title: "Romanized Nepali"
|
| 19 |
-
- text: "म
|
| 20 |
example_title: "Devanagari Nepali"
|
| 21 |
-
- text: "
|
| 22 |
example_title: "Informal English"
|
| 23 |
model-index:
|
| 24 |
- name: SETU
|
|
@@ -31,7 +31,7 @@ model-index:
|
|
| 31 |
name: Nepali-English Mixed Dataset
|
| 32 |
metrics:
|
| 33 |
- type: bleu
|
| 34 |
-
value:
|
| 35 |
name: BLEU
|
| 36 |
library_name: transformers
|
| 37 |
---
|
|
|
|
| 14 |
- onnx
|
| 15 |
pipeline_tag: translation
|
| 16 |
widget:
|
| 17 |
+
- text: "mero name ramesh ho"
|
| 18 |
example_title: "Romanized Nepali"
|
| 19 |
+
- text: "सामाजिक मिडिया र ग्राउण्ड वास्तविकता फरक छ।"
|
| 20 |
example_title: "Devanagari Nepali"
|
| 21 |
+
- text: "what is your nam"
|
| 22 |
example_title: "Informal English"
|
| 23 |
model-index:
|
| 24 |
- name: SETU
|
|
|
|
| 31 |
name: Nepali-English Mixed Dataset
|
| 32 |
metrics:
|
| 33 |
- type: bleu
|
| 34 |
+
value: 49.5
|
| 35 |
name: BLEU
|
| 36 |
library_name: transformers
|
| 37 |
---
|