Update app.py

app.py

@@ -1,4 +1,71 @@
 import gradio as gr
+from transformers import AutoTokenizer, AutoModel
+from sklearn.metrics.pairwise import cosine_similarity
+import torch
+import numpy as np
+from gradio_client import Client
+from functools import lru_cache
+
+# Cache the model and tokenizer using lru_cache
+@lru_cache(maxsize=1)
+def load_model_and_tokenizer():
+    model_name = "./all-MiniLM-L6-v2"  # Replace with your Space and model path
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModel.from_pretrained(model_name)
+    return tokenizer, model
+
+# Load the model and tokenizer
+tokenizer, model = load_model_and_tokenizer()
+
+# Precompute label embeddings
+labels = [
+    "aerospace", "anatomy", "anthropology", "art", 
+    "automotive", "blockchain", "biology", "chemistry", 
+    "cryptocurrency", "data science", "design", "e-commerce",
+    "education", "engineering", "entertainment", "environment",
+    "fashion", "finance", "food commerce", "gaming",
+    "healthcare", "history", "information technology", 
+    "legal", "machine learning", "marketing", "medicine",
+    "music", "philosophy", "physics", "politics", "real estate", "retail", 
+    "robotics", "social media", "sports", "technical",
+    "tourism", "travel"
+]
+
+tones = [
+    "formal", "positive", "negative", "poetic", "polite", "subtle", "casual", "neutral",
+    "informal", "pompous", "sustained", "rude", "sustained",
+    "sophisticated", "playful", "serious", "friendly"
+]
+
+styles = [
+    "poetry", "novel", "theater", "slang", "speech", "keywords", "html", "programming"
+]
+
+gender_number = [
+    "masculine singular", "masculine plural", "feminine singular", "feminine plural"
+]
+
+@lru_cache(maxsize=1)
+def precompute_label_embeddings():
+    inputs = tokenizer(labels, padding=True, truncation=True, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+    return outputs.last_hidden_state.mean(dim=1).numpy()  # Mean pooling for embeddings
+
+label_embeddings = precompute_label_embeddings()
+
+# Softmax function to convert scores to probabilities
+def softmax(x):
+    exp_x = np.exp(x - np.max(x))  # Subtract max for numerical stability
+    return exp_x / exp_x.sum()
+
+# Function to detect context
+def detect_context(input_text, threshold=0.03):
+    # Encode the input text
+    inputs = tokenizer([input_text], padding=True, truncation=True, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+    input_embedding = outputs.last_hidden_state.mean(dim=1).numpy()  # Mean pooling for embedding
 
     # Compute cosine similarities
     similarities = cosine_similarity(input_embedding, label_embeddings)[0]
@@ -24,7 +91,7 @@ def get_translation_client(context):
     Returns the appropriate Hugging Face Space client for the given context.
     For now, all contexts use the same mock space.
     """
-    return Client("Frenchizer/space_18")  # Replace with actual Space paths for each context
+    return Client("Frenchizer/space_7")  # Replace with actual Space paths for each context
 
 def translate_text(input_text, context):
     """