Update app.py

app.py

@@ -8,6 +8,35 @@ import gradio as gr
 import google.auth
 from google.auth.transport.requests import Request
 
+
+def update_text_from_dictionary(text, dictionary_path="./en_hi.dict", initial_lookup=True):
+    if not dictionary_path:
+        return texts
+
+    with open(dictionary_path) as f:
+        lines = f.read().splitlines()
+    
+    updated_lines = list(map(lambda x: x.split("|"), lines))
+    
+    initial_pass_dict = {}
+    final_pass_dict = {}
+    for initial, incorrect, correct in updated_lines:
+        initial_pass_dict[initial] = correct
+        initial_pass_dict[initial+"."] = correct+"."
+        initial_pass_dict[initial+"?"] = correct+"?"
+        initial_pass_dict[initial+","] = correct+","
+        final_pass_dict[incorrect] = correct
+        final_pass_dict[incorrect+"."] = correct+"."
+        final_pass_dict[incorrect+"?"] = correct+"?"
+        final_pass_dict[incorrect+","] = correct+","
+
+    replacable_dict = initial_pass_dict if initial_lookup else final_pass_dict
+    print(f"Original [{initial_lookup}]: ", text)
+    new_text = " ".join([replacable_dict.get(t, t) for t in text.split()])
+    print(f"New [{initial_lookup}]: ", text)
+    return new_text
+
+
 def get_google_token():
     credentials, project = google.auth.load_credentials_from_dict(
         json.loads(os.environ.get('GCP_FINETUNE_KEY')),
@@ -62,7 +91,9 @@ def clean_hindi_transliterated_text(text):
     text = text.replace('`', '').replace("output:", "")
     for o, n in updates:
         text = text.replace(o, n)
-    return text.strip().strip("'").strip('"')
+    final_text = text.strip().strip("'").strip('"')
+    result_text = update_text_from_dictionary(final_text)
+    return result_text
 
 
 def dubpro_english_transliteration(text, call_gpt):