pydantic

app.py

@@ -50,10 +50,79 @@ def get_score(user_text, language):
     score = optimized_scorer.score(user_text, language)
     formatted_score = f"{score:.4g}"
     loaded_languages = optimized_scorer.get_loaded_languages()
-    return f'<div class="nice-box"> Score: {formatted_score}</div>', f"Currently loaded languages: {', '.join(loaded_languages)}"
+    display_loaded_languages = [('Currently loaded languages:', None)]
+    for language in loaded_languages:
+        display_loaded_languages.append((language_map[language], language))
+        display_loaded_languages.append((' ', None))
+    return f'<div class="nice-box"> Score: {formatted_score}</div>', display_loaded_languages
 
 language_options = ['am', 'ar', 'bg', 'bn', 'cs', 'da', 'de', 'el', 'en', 'es', 'fa', 'fi', 'fr', 'gu', 'ha', 'hi', 'hu', 'id', 'it', 'ja', 'jv', 'kn', 'ko', 'lt', 'mr', 'nl', 'no', 'yo', 'zh']
 
+language_map = {
+    'am': 'Amharic',
+    'ar': 'Arabic',
+    'bg': 'Bulgarian',
+    'bn': 'Bengali',
+    'cs': 'Czech',
+    'da': 'Danish',
+    'de': 'German',
+    'el': 'Greek',
+    'en': 'English',
+    'es': 'Spanish',
+    'fa': 'Persian',
+    'fi': 'Finnish',
+    'fr': 'French',
+    'gu': 'Gujarati',
+    'ha': 'Hausa',
+    'hi': 'Hindi',
+    'hu': 'Hungarian',
+    'id': 'Indonesian',
+    'it': 'Italian',
+    'ja': 'Japanese',
+    'jv': 'Javanese',
+    'kn': 'Kannada',
+    'ko': 'Korean',
+    'lt': 'Lithuanian',
+    'mr': 'Marathi',
+    'nl': 'Dutch',
+    'no': 'Norwegian',
+    'yo': 'Yoruba',
+    'zh': 'Chinese'
+}
+
+color_map = {
+    "am": "green",     # Ethiopia's flag has green
+    "ar": "black",     # Many Arab flags feature black
+    "bg": "white",     # Bulgaria's flag has white
+    "bn": "green",     # Bangladesh's flag is green and red
+    "cs": "blue",      # Czech Republic's flag has blue
+    "da": "red",       # Denmark's flag is red and white
+    "de": "black",     # Germany's flag has black
+    "el": "blue",      # Greece's flag has blue
+    "en": "red",       # UK/US flags have red
+    "es": "yellow",    # Spain's flag has yellow
+    "fa": "green",     # Iran's flag has green
+    "fi": "blue",      # Finland's flag is blue and white
+    "fr": "blue",      # France's flag has blue
+    "gu": "saffron",   # India (Gujarat) flag's color
+    "ha": "green",     # Nigeria's flag has green
+    "hi": "orange",    # India's flag has orange
+    "hu": "red",       # Hungary's flag has red
+    "id": "red",       # Indonesia's flag is red and white
+    "it": "green",     # Italy's flag has green
+    "ja": "red",       # Japan's flag has a red sun
+    "jv": "brown",     # Associated with traditional Javanese culture
+    "kn": "yellow",    # Karnataka (Indian state) flag has yellow
+    "ko": "blue",      # South Korea's flag has blue
+    "lt": "yellow",    # Lithuania's flag has yellow
+    "mr": "saffron",   # Marathi culture often uses saffron
+    "nl": "orange",    # The Netherlands is often associated with orange
+    "no": "red",       # Norway's flag is red, white, and blue
+    "yo": "green",     # Nigeria's flag for Yoruba-speaking people
+    "zh": "red"        # China's flag is red
+}
+
+
 css = '''
 #gen_btn{height: 100%}
 #title{text-align: center}
@@ -95,13 +164,6 @@ with gr.Blocks(theme=theme, css=css) as demo:
     )
     with gr.Row():
         user_text = gr.Textbox(label='Input text', placeholder='Type something here...')
-        language_choice = gr.Dropdown(
-            choices=language_options,
-            label="Choose a language",
-            info="Type to search",
-            value="en",
-            allow_custom_value=True,
-        )
         with gr.Column(scale=0):
             submit_btn = gr.Button("Submit")
             score = gr.HTML(
@@ -109,17 +171,36 @@ with gr.Blocks(theme=theme, css=css) as demo:
                 label="Output"
             )
     
-    loaded_languages = gr.Markdown("Currently loaded languages: en")
+    with gr.Row():
+        language_choice = gr.Dropdown(
+                choices=language_options,
+                label="Choose a language",
+                info="Type to search",
+                value="en",
+                allow_custom_value=True,
+            )
+        
+        loaded_languages = gr.HighlightedText(
+            value = [('Currently loaded languages:', None), ('English', 'en')],
+            label="",
+            combine_adjacent=True,
+            show_legend=False, #True,
+            color_map=color_map)
+    
+    #loaded_languages = gr.Markdown("Currently loaded languages: en")
     
     gr.Examples(examples=example_inputs, inputs=user_text)
     
     gr.Markdown(
     """
+    ---
+    
+    ## 🛈 **Additional Information**
+    This model can also be found on [Github](https://github.com/lightblue-tech/shitsu) and has its own pip installable package.
+    
     This model is based on fasttext embeddings, meaning that it can be used on large amounts of data with limited compute quickly.
 
     This scorer can be used to filter useful information from large text corpora in many languages.  
-    
-    This model can also be found on [Github](https://github.com/lightblue-tech/shitsu) and has its own pip installable package. 
     """
     )
     

requirements.txt

@@ -1,3 +1,4 @@
 git+https://github.com/lightblue-tech/shitsu.git
 hf-transfer
-huggingface_hub[hf_transfer]
+huggingface_hub[hf_transfer]
+pydantic