Update app.py

app.py

@@ -44,7 +44,7 @@ class GradioInference:
 
 
     
-    def __call__(self, link, lang, size):
+    def __call__(self, link, lang, size, progress=gr.Progress()):
         """
         Call the Gradio Inference python class.
         This class gets access to a YouTube video using python's library Pytube and downloads its audio.
@@ -55,6 +55,7 @@ class GradioInference:
             - Sentiment Analysis: using Hugging Face's default sentiment classifier
             - WordCloud: using the wordcloud python library.
         """
+        progress(0, desc="Starting analysis")
         if self.yt is None:
             self.yt = YouTube(link)
         
@@ -68,9 +69,11 @@ class GradioInference:
             self.loaded_model = whisper.load_model(size)
             self.current_size = size
 
+        progress(0.20, desc="Transcribing")
         # Transcribe the audio extracted from pytube
         results = self.loaded_model.transcribe(path, language=lang)
 
+        progress(0.35, desc="Summarizing")
         # Perform summarization on the transcription
         transcription_summary = self.summarizer(
             results["text"], max_length=150, min_length=30, do_sample=False
@@ -101,7 +104,7 @@ class GradioInference:
         )
         #### Fin prueba
 
-        
+        progress(0.50, desc="Extracting Keywords")
         # Extract keywords using VoiceLabT5
         task_prefix = "Keywords: "
         input_sequence = task_prefix + results["text"]
@@ -114,9 +117,11 @@ class GradioInference:
         predicted = self.keyword_tokenizer.decode(output[0], skip_special_tokens=True)
         keywords = [x.strip() for x in predicted.split(",") if x.strip()]
 
+        progress(0.75, desc="Extracting Sentiment")
         # Sentiment label
         label = self.classifier(summary)[0]["label"]
-        
+
+        progress(0.90, desc="Generating Wordcloud")
         # Generate WordCloud object
         wordcloud = WordCloud(colormap = "Oranges").generate(results["text"])