Update app.py

app.py

@@ -3,16 +3,17 @@ from indic_transliteration import sanscript
 from indic_transliteration.sanscript import transliterate
 from transformers import pipeline
 
-# 1. Load models (public models)
+# 1. Load public models
+# Public Hindi sentiment & emotion models (authentication-free)
 emotion_model = pipeline(
     "text-classification",
-    model="monsoon-nlp/hindi-emotion",  # Public Hindi emotion model
+    model="l3cube-pune/hindi-emotion",  # Public Hindi emotion model
     return_all_scores=True
 )
 
 sentiment_model = pipeline(
     "text-classification",
-    model="madhav112/hindi-sentiment-analysis",  # Public Hindi sentiment model
+    model="nlptown/bert-base-multilingual-uncased-sentiment",  # Multilingual sentiment model
     return_all_scores=True
 )
 
@@ -33,55 +34,48 @@ def normalize_hindi(text: str) -> str:
         text = text.replace(wrong, right)
     return text
 
-# 4. Emoji & Label mapping
+# 4. Emoji mapping
 EMOJI_MAP = {
-    "anger": "😡",
-    "disgust": "🤢",
-    "fear": "😱",
-    "joy": "😄",
-    "neutral": "😐",
-    "sadness": "😢",
-    "surprise": "😲"
+    "anger":"😡","disgust":"🤢","fear":"😱","joy":"😄","neutral":"😐","sadness":"😢","surprise":"😲"
 }
 
 SENTIMENT_MAP = {
-    "LABEL_0": "😞 Negative",
-    "LABEL_1": "😐 Neutral",
-    "LABEL_2": "😃 Positive"
+    "1":"😞 Negative",
+    "2":"😐 Slightly Negative",
+    "3":"😐 Neutral",
+    "4":"😃 Positive",
+    "5":"😃 Very Positive"
 }
 
 # 5. Full pipeline
 def analyze_text_visual(hinglish_text: str):
-    # Hinglish → Hindi → Normalize
     hindi_text = normalize_hindi(hinglish_to_hindi(hinglish_text))
     
-    # Emotion
+    # Emotion analysis
     emotion_scores = emotion_model(hindi_text)
     top_emotion = max(emotion_scores[0], key=lambda x: x['score'])
-    emotion_result = f"{EMOJI_MAP.get(top_emotion['label'], '')} {top_emotion['label']} ({top_emotion['score']:.2f})"
     
-    # Sentiment
+    # Sentiment analysis
     sentiment_scores = sentiment_model(hindi_text)
     top_sentiment = max(sentiment_scores[0], key=lambda x: x['score'])
-    sentiment_result = f"{SENTIMENT_MAP.get(top_sentiment['label'], '')} ({top_sentiment['score']:.2f})"
     
-    return {
+    # Prepare user-friendly output
+    output = {
+        "Hinglish Input": hinglish_text,
         "Hindi Text": hindi_text,
-        "Top Emotion": emotion_result,
-        "Top Sentiment": sentiment_result
+        "Top Emotion": f"{EMOJI_MAP.get(top_emotion['label'], '')} {top_emotion['label']} ({top_emotion['score']:.2f})",
+        "Top Sentiment": f"{SENTIMENT_MAP.get(str(int(top_sentiment['label'][-1])), '')} ({top_sentiment['score']:.2f})"
     }
+    return output
 
-# 6. Gradio Interface
+# 6. Gradio interface
 iface = gr.Interface(
     fn=analyze_text_visual,
-    inputs=gr.Textbox(label="Hinglish Text"),
-    outputs=[
-        gr.Textbox(label="Hindi Text"),
-        gr.Textbox(label="Top Emotion"),
-        gr.Textbox(label="Top Sentiment")
-    ],
-    title="Hindi Emotion & Sentiment Analyzer",
-    description="Hinglish input से Hindi में convert करके Emotion और Sentiment दिखाएँ।"
+    inputs="text",
+    outputs="json",
+    title="Hinglish → Hindi Emotion & Sentiment Analysis",
+    description="Type Hinglish text, see Hindi transliteration, top emotion and sentiment with emojis."
 )
 
 iface.launch()
+