Instructions to use Prosho/sentinel-src-25 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Prosho/sentinel-src-25 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="Prosho/sentinel-src-25")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prosho/sentinel-src-25", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,9 +15,39 @@ license: apache-2.0
|
|
| 15 |
|
| 16 |
</div>
|
| 17 |
|
| 18 |
-
<div style="display:flex; justify-content: center; align-items: center; flex-
|
| 19 |
-
<a href="https://
|
| 20 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
</div>
|
| 22 |
|
| 23 |
This repository contains the **SENTINEL<sub>SRC</sub>** metric model used for Difficulty Sampling at the [WMT25 General Machine Translation Shared Task](https://www2.statmt.org/wmt25/translation-task.html), and analyzed in our paper **Estimating Machine Translation Difficulty**.
|
|
|
|
| 15 |
|
| 16 |
</div>
|
| 17 |
|
| 18 |
+
<div style="display: flex; justify-content: center; align-items: center; gap: 8px; flex-wrap: wrap;">
|
| 19 |
+
<a href="https://2025.emnlp.org/" style="display: flex;">
|
| 20 |
+
<img
|
| 21 |
+
src="https://img.shields.io/badge/EMNLP-2025-4b44ce.svg"
|
| 22 |
+
alt="EMNLP 2025"
|
| 23 |
+
height="20"
|
| 24 |
+
style="display: block;"
|
| 25 |
+
>
|
| 26 |
+
</a>
|
| 27 |
+
<a href="https://aclanthology.org/2025.findings-emnlp.1317/" style="display: flex;">
|
| 28 |
+
<img
|
| 29 |
+
src="https://img.shields.io/badge/paper-ACL--anthology-B31B1B.svg"
|
| 30 |
+
alt="ACL Anthology paper"
|
| 31 |
+
height="20"
|
| 32 |
+
style="display: block;"
|
| 33 |
+
>
|
| 34 |
+
</a>
|
| 35 |
+
<a href="https://huggingface.co/collections/Prosho/translation-difficulty-estimators-6816665c008e1d22426eb6c4" style="display: flex;">
|
| 36 |
+
<img
|
| 37 |
+
src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Collection-FCD21D"
|
| 38 |
+
alt="Hugging Face collection"
|
| 39 |
+
height="20"
|
| 40 |
+
style="display: block;"
|
| 41 |
+
>
|
| 42 |
+
</a>
|
| 43 |
+
<a href="https://www.apache.org/licenses/LICENSE-2.0" style="display: flex;">
|
| 44 |
+
<img
|
| 45 |
+
src="https://img.shields.io/badge/License-Apache%202.0-green"
|
| 46 |
+
alt="Apache 2.0 license"
|
| 47 |
+
height="20"
|
| 48 |
+
style="display: block;"
|
| 49 |
+
>
|
| 50 |
+
</a>
|
| 51 |
</div>
|
| 52 |
|
| 53 |
This repository contains the **SENTINEL<sub>SRC</sub>** metric model used for Difficulty Sampling at the [WMT25 General Machine Translation Shared Task](https://www2.statmt.org/wmt25/translation-task.html), and analyzed in our paper **Estimating Machine Translation Difficulty**.
|