Spaces:
Running
Running
Slimmed down markdown text and removed all markdown links (broken in Gradio)
Browse files
app.py
CHANGED
|
@@ -128,10 +128,8 @@ def classify(text, file):
|
|
| 128 |
with gr.Blocks() as demo:
|
| 129 |
gr.Markdown("# ScandiProb: Hybrid Language ID Classifier")
|
| 130 |
gr.Markdown("### By Ian Rodriguez")
|
| 131 |
-
gr.Markdown("Enter text or upload a file to output independent probabilities that it is written in **Norwegian**, **Swedish**, **Danish**, or **None of the Above / Non-Scandinavian**. Only first 512 tokens of input will be used.")
|
| 132 |
-
gr.Markdown("This model utilizes a fine-tuned
|
| 133 |
-
gr.Markdown("[This project is licensed under AGPL-3.0.](https://www.gnu.org/licenses/agpl-3.0.en.html)", sanitize_html=False)
|
| 134 |
-
gr.Markdown("([GitHub](https://github.com/cloudeerie/scandiprob) | [Kaggle Notebooks](https://www.kaggle.com/code/cloudeerie/scandiprob/) | [Raw Model Page](https://huggingface.co/ianro04/ScandiProb))", sanitize_html=False)
|
| 135 |
|
| 136 |
with gr.Row():
|
| 137 |
with gr.Column():
|
|
|
|
| 128 |
with gr.Blocks() as demo:
|
| 129 |
gr.Markdown("# ScandiProb: Hybrid Language ID Classifier")
|
| 130 |
gr.Markdown("### By Ian Rodriguez")
|
| 131 |
+
gr.Markdown("Enter text or upload a file to output independent probabilities that it is written in **Norwegian**, **Swedish**, **Danish**, or **None of the Above / Non-Scandinavian**. Only the first 512 tokens of input will be used.")
|
| 132 |
+
gr.Markdown("This model utilizes a fine-tuned *ScandiBERT*, trained on limited amounts of *OPUS-100*, and combined with regex-enforced heuristics. Achieves ~93% macro-F1 score on OPUS-100 test set and ~84% macro-F1 score against the comprehensive SLIDE eval set, with a fraction of the training data used in SLIDE.")
|
|
|
|
|
|
|
| 133 |
|
| 134 |
with gr.Row():
|
| 135 |
with gr.Column():
|