Commit ·
1fce961
0
Parent(s):
Add test-gradio HF Space for codemix PII detector
Browse filesGradio UI deployed to huggingface.co/spaces/Ramosh99/test
using the Ramosh99/mixcode_pii_detector model.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- .gitattributes +35 -0
- README.md +18 -0
- app.py +55 -0
- requirements.txt +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: Sinhala-English Codemix PII Detector
|
| 3 |
+
emoji: 🔒
|
| 4 |
+
colorFrom: green
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: gradio
|
| 7 |
+
sdk_version: 6.20.0
|
| 8 |
+
python_version: '3.12'
|
| 9 |
+
app_file: app.py
|
| 10 |
+
pinned: false
|
| 11 |
+
license: apache-2.0
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# Sinhala-English Codemix PII Detector
|
| 15 |
+
|
| 16 |
+
Detects PII entities in Sinhala-English code-mixed text using the `Ramosh99/mixcode_pii_detector` model (XLM-RoBERTa token-classification).
|
| 17 |
+
|
| 18 |
+
Supported entity types: PERSON, ORG, PHONE, EMAIL, NIC, LOCATION, etc.
|
app.py
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import spaces
|
| 2 |
+
import os
|
| 3 |
+
import gradio as gr
|
| 4 |
+
import torch
|
| 5 |
+
from transformers import pipeline
|
| 6 |
+
|
| 7 |
+
ner = pipeline(
|
| 8 |
+
"ner",
|
| 9 |
+
model="Ramosh99/mixcode_pii_detector",
|
| 10 |
+
aggregation_strategy="average",
|
| 11 |
+
token=os.getenv("HF_TOKEN"),
|
| 12 |
+
)
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
@spaces.GPU
|
| 16 |
+
def detect_pii(text):
|
| 17 |
+
if not text.strip():
|
| 18 |
+
return {"text": text, "entities": []}
|
| 19 |
+
|
| 20 |
+
raw = ner(text)
|
| 21 |
+
entities = []
|
| 22 |
+
for item in raw:
|
| 23 |
+
label = item.get("entity_group", "")
|
| 24 |
+
if label.startswith(("B-", "I-")):
|
| 25 |
+
label = label[2:]
|
| 26 |
+
entities.append({
|
| 27 |
+
"entity": label,
|
| 28 |
+
"start": item["start"],
|
| 29 |
+
"end": item["end"],
|
| 30 |
+
"score": round(float(item["score"]), 4),
|
| 31 |
+
})
|
| 32 |
+
|
| 33 |
+
highlighted = [{"entity": item["entity"], "start": item["start"], "end": item["end"]} for item in entities]
|
| 34 |
+
return {"text": text, "entities": highlighted}
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
demo = gr.Interface(
|
| 38 |
+
fn=detect_pii,
|
| 39 |
+
inputs=gr.Textbox(
|
| 40 |
+
label="Input Text",
|
| 41 |
+
placeholder="Enter Sinhala-English codemixed text...",
|
| 42 |
+
lines=4,
|
| 43 |
+
),
|
| 44 |
+
outputs=gr.HighlightedText(label="Detected PII Entities"),
|
| 45 |
+
title="Sinhala-English Codemix PII Detector",
|
| 46 |
+
description="Detects PII entities (PERSON, ORG, PHONE, EMAIL, NIC, etc.) in Sinhala-English code-mixed text using the Ramosh99/mixcode_pii_detector model.",
|
| 47 |
+
examples=[
|
| 48 |
+
["Mage name Kamal, man wada karanne MAS Holdings eke, phone 071-1234567"],
|
| 49 |
+
["මගේ email address kamal.perera@gmail.com, NIC number 199912345678"],
|
| 50 |
+
["I live in Colombo and my phone number is 0771234567"],
|
| 51 |
+
],
|
| 52 |
+
flagging_mode="never",
|
| 53 |
+
)
|
| 54 |
+
|
| 55 |
+
demo.launch()
|
requirements.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers>=4.40.0
|
| 2 |
+
torch>=2.2.0
|
| 3 |
+
sentencepiece>=0.2.0
|