Update app.py

app.py

@@ -25,7 +25,7 @@ class GradioInference:
         # Initialize Pytube Object
         self.yt = None
 
-        # Initialize summary model
+        # Initialize summary model for English
         self.summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
         # Initialize VoiceLabT5 model and tokenizer
@@ -39,7 +39,7 @@ class GradioInference:
         # Sentiment Classifier
         self.classifier = pipeline("text-classification", model="lxyuan/distilbert-base-multilingual-cased-sentiments-student", return_all_scores=False)
 
-        
+        # Initialize Multilingual summary model 
         self.tokenizer = AutoTokenizer.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
         self.model = AutoModelForSeq2SeqLM.from_pretrained("csebuetnlp/mT5_multilingual_XLSum")
 
@@ -71,10 +71,12 @@ class GradioInference:
             self.current_size = size
 
         progress(0.20, desc="Transcribing")
+        
         # Transcribe the audio extracted from pytube
         results = self.loaded_model.transcribe(path, language=lang)
 
         progress(0.40, desc="Summarizing")
+        
         # Perform summarization on the transcription
         transcription_summary = self.summarizer(
             results["text"], max_length=150, min_length=30, do_sample=False
@@ -106,6 +108,7 @@ class GradioInference:
         #### Fin prueba
 
         progress(0.50, desc="Extracting Keywords")
+        
         # Extract keywords using VoiceLabT5
         task_prefix = "Keywords: "
         input_sequence = task_prefix + results["text"]
@@ -135,6 +138,7 @@ class GradioInference:
         formatted_sentiment = sentiment_emojis.get(label, label)
 
         progress(0.90, desc="Generating Wordcloud")
+        
         # Generate WordCloud object
         wordcloud = WordCloud(colormap = "Oranges").generate(results["text"])
 
@@ -166,7 +170,7 @@ class GradioInference:
         - link: a YouTube URL.
         """
         if not link:
-            return "", "..."
+            return None, "..."
             
         self.yt = YouTube(link)
         return self.yt.thumbnail_url, self.yt.title
@@ -182,6 +186,7 @@ class GradioInference:
             - WordCloud: using the wordcloud python library.
         """
         progress(0, desc="Starting analysis")
+        
         if lang == "none":
             lang = None
 
@@ -190,9 +195,11 @@ class GradioInference:
             self.current_size = size
 
         progress(0.20, desc="Transcribing")
+        
         results = self.loaded_model.transcribe(audio_file, language=lang)
 
         progress(0.40, desc="Summarizing")
+        
         # Perform summarization on the transcription
         transcription_summary = self.summarizer(
             results["text"], max_length=150, min_length=30, do_sample=False
@@ -224,6 +231,7 @@ class GradioInference:
         #### Fin prueba
 
         progress(0.50, desc="Extracting Keywords")
+        
         # Extract keywords using VoiceLabT5
         task_prefix = "Keywords: "
         input_sequence = task_prefix + results["text"]
@@ -282,6 +290,7 @@ title = "YouTube Insights"
 description = "Your AI-powered video analytics tool"
 
 block = gr.Blocks()
+
 with block as demo:
     gr.HTML(
         """
@@ -298,6 +307,7 @@ with block as demo:
     with gr.Group():
         with gr.Tab("From YouTube 📹"):
             with gr.Box():
+                
                 with gr.Row().style(equal_height=True):
                     size = gr.Dropdown(
                         label="Model Size", choices=gio.sizes, value="base"
@@ -309,6 +319,7 @@ with block as demo:
                     label="YouTube Link", placeholder="Enter YouTube link..."
                 )
                 title = gr.Label(label="Video Title")
+                
                 with gr.Row().style(equal_height=True):
                     img = gr.Image(label="Thumbnail", rounded=True)
                     text = gr.Textbox(
@@ -316,6 +327,7 @@ with block as demo:
                         placeholder="Transcription Output...",
                         lines=10,
                     ).style(show_copy_button=True, container=True)
+                    
                 with gr.Row().style(equal_height=True):
                     summary = gr.Textbox(
                         label="Summary", placeholder="Summary Output...", lines=5
@@ -325,6 +337,7 @@ with block as demo:
                     ).style(show_copy_button=True, container=True)
                     label = gr.Label(label="Sentiment Analysis")
                     wordcloud_image = gr.Image(label="WordCloud")
+                    
                 with gr.Row().style(equal_height=True):
                     clear = gr.ClearButton(
                         [link, title, img, text, summary, keywords, label, wordcloud_image], scale=1, value="Clear 🗑️", rounded=True
@@ -339,6 +352,7 @@ with block as demo:
 
         with gr.Tab("From Audio file 🎙️"):
             with gr.Box():
+                
                 with gr.Row().style(equal_height=True):
                     size = gr.Dropdown(
                         label="Model Size", choices=gio.sizes, value="base"
@@ -347,12 +361,14 @@ with block as demo:
                         label="Language (Optional)", choices=gio.langs, value="none"
                     )
                 audio_file = gr.Audio(type="filepath")
+                
                 with gr.Row().style(equal_height=True):
                     text = gr.Textbox(
                         label="Transcription",
                         placeholder="Transcription Output...",
                         lines=10,
                     ).style(show_copy_button=True, container=False)
+                    
                 with gr.Row().style(equal_height=True):
                     summary = gr.Textbox(
                         label="Summary", placeholder="Summary Output", lines=5
@@ -362,6 +378,7 @@ with block as demo:
                     )
                     label = gr.Label(label="Sentiment Analysis")
                     wordcloud_image = gr.Image(label="WordCloud")
+                    
                 with gr.Row().style(equal_height=True):
                     clear = gr.ClearButton([audio_file,text, summary, keywords, label, wordcloud_image], scale=1, value="Clear 🗑️",rounded=True)
                     btn = gr.Button(
@@ -422,6 +439,9 @@ with block:
         """
         <div style="text-align: center; max-width: 500px; margin: 0 auto;">
           <p style="margin-bottom: 10px; font-size: 96%">
+            Trabajo de Fin de Máster - Grupo 3
+          </p>
+          <p style="margin-bottom: 10px; font-size: 90%">
             2023 Master in Big Data & Data Science - Universidad Complutense de Madrid
           </p>
         </div>