Create app.py

app.py

@@ -0,0 +1,36 @@
+import emoji_data_python
+import pickle
+from tqdm import tqdm
+from sentence_transformers import SentenceTransformer
+import numpy as np
+model = SentenceTransformer('all-mpnet-base-v2')
+try:
+    with open('embeddings_list.pkl', 'rb') as f:
+        embeddings_list = pickle.load(f)
+except:
+    embeddings_list = []
+emojis_to_compute = [e for e in emoji_data_python.emoji_data if e.unified not in [e[0] for e in embeddings_list]]
+if emojis_to_compute:
+    for e in tqdm(emojis_to_compute, desc='Computing embeddings'):
+        strings = [n.replace('_', ' ').strip() for n in e.short_names] + [e.name.lower()]
+        for s in strings:
+            embedding = model.encode(s)
+            embeddings_list.append((e.unified, embedding))
+    with open('embeddings_list.pkl', 'wb') as f:
+        pickle.dump(embeddings_list, f)
+def closest_emoji(text):
+    text_embedding = model.encode(text)
+    closest_emoji = None
+    closest_distance = np.inf
+    for emoji, emoji_embedding in embeddings_list:
+        distance = np.linalg.norm(text_embedding - emoji_embedding)
+        if distance < closest_distance:
+            closest_distance = distance
+            closest_emoji = emoji
+    return emoji_data_python.unified_to_char(closest_emoji)
+import gradio as gr
+emoji_input = gr.inputs.Textbox(label='text in')
+emoji_output = gr.outputs.Textbox(label='emoji out')
+iface = gr.Interface(fn=closest_emoji, inputs=emoji_input, outputs=emoji_output, 
+                     title='text to emoji')
+iface.launch()