removed gargabe roberta

app.py

@@ -1,7 +1,7 @@
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 import torch
-from transformers import RobertaTokenizer, RobertaForSequenceClassification
+from transformers import BertTokenizer, BertForSequenceClassification
 from torch.nn.functional import softmax
 
 app = FastAPI(
@@ -14,8 +14,8 @@ app = FastAPI(
 class ContactDetector:
     def __init__(self):
         cache_dir = "/app/model_cache"
-        self.tokenizer = RobertaTokenizer.from_pretrained('roberta-base', use_fast=True, cache_dir=cache_dir)
-        self.model = RobertaForSequenceClassification.from_pretrained('roberta-base', num_labels=2, cache_dir=cache_dir)
+        self.tokenizer = BertTokenizer.from_pretrained('bert-base-uncased', cache_dir=cache_dir)
+        self.model = BertForSequenceClassification.from_pretrained('bert-base-uncased', num_labels=2, cache_dir=cache_dir)
         self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
         self.model.to(self.device)
         self.model.eval()

test.py

@@ -0,0 +1,46 @@
+import requests
+import json
+
+test_texts = [
+    "My email is [email protected]",
+    "Call me at (123) 456-7890",
+    "I live at 123 Main St, New York, NY 10001",
+    "Let's meet at the park tomorrow",
+    "My phone number is 555-1234",
+    "You can reach me on Skype: user123",
+    "Reach me at one two three dot four five six dot seven eight nine zero",
+    "My handle is at_symbol_user_123 on that bird app",
+    "Drop me a line: first_name (dot) last_name [at] big_search_engine (dot) com",
+    "Ring me: area code seven-seven-seven then half a dozen, a quartet, and two pairs",
+    "Find me on the gram: @cool_user_2023",
+    "I'm on that professional network, just search for John Doe from Acme Corp",
+    "Send a raven to Winterfell, care of the Stark family",
+    "Ping me on IRC: /msg CoolDude42",
+    "You can find me at one two three Fake Street, Anytown, State of Confusion",
+    "My digits are the first ten prime numbers in order",
+    "Contact info: tango alpha november golf oscar at yankee alpha hotel oscar oscar dot charlie oscar mike",
+    "Beep me at 555 (not a real area code) then 867-5309",
+    "I'm on that app where messages disappear, username: GhostWriter99",
+    "Reach out via electronic mail to 'surname underscore initial' at that fruit company dot com",
+    "Call me maybe? Area code is square root of 169, then 555-CHAT",
+]
+
+url = "https://vidhitmakvana1-contact-sharing-recognizer-api.hf.space/detect_contact"
+
+for text in test_texts:
+    payload = {"text": text}
+    headers = {"Content-Type": "application/json"}
+
+    response = requests.post(url, data=json.dumps(payload), headers=headers)
+
+    if response.status_code == 200:
+        result = response.json()
+        print(f"Text: {result['text']}")
+        print(f"Contact Probability: {result['contact_probability']:.4f}")
+        print(f"Is Contact Info: {result['is_contact_info']}")
+        print("---")
+    else:
+        print(f"Error for text: {text}")
+        print(f"Status code: {response.status_code}")
+        print(f"Response: {response.text}")
+        print("---")