Update app.py

app.py

@@ -40,20 +40,6 @@ def get_transcript(file):
     transcript = data['results'].values[1][0]['transcript']
     transcript = transcript.lower()
     return transcript
-#    
-"""preprocess tags"""
-if tags:
-  tags = [x.lower().strip() for x in tags.split(",")]
-  tags_tokens = concat_tokens(tags)
-  tags_tokens.pop("KPS")
-  with torch.no_grad():
-    outputs_tags = model(**tags_tokens)
-  pools_tags = pool_embeddings(outputs_tags, tags_tokens).detach().numpy()
-  token_dict = {}
-  for tag,embedding in zip(tags,pools_tags):
-    token_dict[tag] = embedding
-
-"""Code related with processing text, extracting KPs, and doing distance to tag"""
 def concat_tokens(sentences):
   tokens = {'input_ids': [], 'attention_mask': [], 'KPS': {}}
   for sentence, values in sentences.items():
@@ -70,6 +56,21 @@ def concat_tokens(sentences):
   tokens['attention_mask'] = torch.stack(tokens['attention_mask'])
   return tokens
   
+"""preprocess tags"""
+if tags:
+  tags = [x.lower().strip() for x in tags.split(",")]
+  tags_tokens = concat_tokens(tags)
+  tags_tokens.pop("KPS")
+  with torch.no_grad():
+    outputs_tags = model(**tags_tokens)
+  pools_tags = pool_embeddings(outputs_tags, tags_tokens).detach().numpy()
+  token_dict = {}
+  for tag,embedding in zip(tags,pools_tags):
+    token_dict[tag] = embedding
+
+"""Code related with processing text, extracting KPs, and doing distance to tag"""
+
+  
 def calculate_weighted_embed_dist(out, tokens, weight, text,kp_dict, idx, exclude_text=False,exclude_words=False):
   sim_dict = {}
   pools = pool_embeddings_count(out, tokens, idx).detach().numpy()