update app

app.py

@@ -5,16 +5,18 @@ from transformers import AutoTokenizer,AutoModelForMaskedLM
 from transformers import pipeline
 import os
 import json
+import random
 
 @st.cache(show_spinner=False,persist=True)
 def load_model(masked_text,model_name):
 
     model = AutoModelForMaskedLM.from_pretrained(model_name, from_flax=True)
     tokenizer = AutoTokenizer.from_pretrained(model_name)
-    # tokenizer.save_pretrained('exported_pytorch_model')
-    # model.save_pretrained('exported_pytorch_model')
     nlp = pipeline('fill-mask', model=model, tokenizer=tokenizer)
-
+    
+    MASK_TOKEN = tokenizer.mask_token
+    
+    masked_text = masked_text.replace("<mask>",MASK_TOKEN)
     result_sentence = nlp(masked_text)
 
     return result_sentence[0]['sequence']
@@ -27,7 +29,7 @@ def main():
     )
 
     models = st.multiselect(
-        "Choose models",
+        "Choose models",                                         
         ['flax-community/roberta-hindi','mrm8488/HindiBERTa','ai4bharat/indic-bert',\
         'neuralspace-reverie/indic-transformers-hi-bert', 
           'surajp/RoBERTa-hindi-guj-san'],
@@ -40,24 +42,40 @@ def main():
     texts = target_text_df['text']
     
     st.sidebar.title("Hindi MLM")
-    masked_text = st.sidebar.selectbox('Select any of the following text',
-     texts)
-    
-    st.write('You selected:', masked_text)
+     
+    pick_random = st.sidebar.checkbox("Pick any random text")
+
+    #st.write('You selected:', masked_text)
     
     results_df = pd.DataFrame(columns = ['Model Name','Masked Text','Filled Masked Text'])
+     
+    model_names = []
+    masked_texts = []
+    filled_masked_texts = []
+    
+    if pick_random:
+        random_text = texts[random.randint(0,texts.shape[0]-1)]
+        masked_text = st.text_area("Please type a masked sentence to fill",random_text)
+    else:
+        select_text = st.sidebar.selectbox('Select any of the following text',\
+     texts)
+        masked_text = st.text_area("Please type a masked sentence to fill",select_text)
 
-    for selected_model in models:
+    if st.button('Fill the Mask!'):
+        with st.spinner("Filling the Mask..."):
+
+            for selected_model in models:
 
-        if st.button('Fill the Mask!'):
-            with st.spinner("Filling the Mask..."):
                 filled_sentence = load_model(masked_text,selected_model)
-                results_df['Model Name'] = selected_model
-                results_df['Masked Text'] = masked_text
-                results_df['Filled Masked Text'] = filled_sentence
+                model_names.append(selected_model)
+                masked_texts.append(masked_text)
+                filled_masked_texts.append(filled_sentence)
 
-    st.table(results_df)
+            results_df['Model Name'] = model_names
+            results_df['Masked Text'] = masked_texts
+            results_df['Filled Masked Text'] = filled_masked_texts
 
-    
+            st.table(results_df)
+            
 if __name__ == "__main__":
     main()

mlm_custom/mlm_test_config.csv

@@ -3,4 +3,4 @@ flax-community/roberta-hindi,,,TRUE,TRUE,TRUE
 mrm8488/HindiBERTa,,,FALSE,TRUE,TRUE
 ai4bharat/indic-bert,,,FALSE,FALSE,FALSE
 neuralspace-reverie/indic-transformers-hi-bert,,,FALSE,TRUE,TRUE
-surajp/RoBERTa-hindi-guj-san,,,FALSE,TRUE,TRUE
+surajp/RoBERTa-hindi-guj-san,,,FALSE,TRUE,TRUE