Update app.py

app.py

@@ -155,7 +155,7 @@ class GradioInference:
         self.yt = YouTube(link)
         return self.yt.thumbnail_url, self.yt.title
 
-    def from_audio_input(self, lang, size, audio_file):
+    def from_audio_input(self, lang, size, audio_file, progress=gr.Progress()):
         """
         Call the Gradio Inference python class.
         Uses it directly the Whisper model to perform Automatic Speech Recognition (i.e Speech-to-Text).
@@ -165,6 +165,7 @@ class GradioInference:
             - Sentiment Analysis: using Hugging Face's default sentiment classifier
             - WordCloud: using the wordcloud python library.
         """
+        progress(0, desc="Starting analysis")
         if lang == "none":
             lang = None
 
@@ -172,8 +173,10 @@ class GradioInference:
             self.loaded_model = whisper.load_model(size)
             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
@@ -203,7 +206,8 @@ class GradioInference:
             clean_up_tokenization_spaces=False
         )
         #### Fin prueba
-        
+
+        progress(0.50, desc="Extracting Keywords")
         # Extract keywords using VoiceLabT5
         task_prefix = "Keywords: "
         input_sequence = task_prefix + results["text"]
@@ -216,9 +220,11 @@ 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(0.80, desc="Extracting Sentiment")
         # Sentiment label    
         label = self.classifier(summary)[0]["label"]
-        
+
+        progress(0.90, desc="Generating Wordcloud")
         # WordCloud object
         wordcloud = WordCloud(colormap = "Oranges").generate(
             results["text"]
@@ -331,7 +337,7 @@ with block as demo:
                 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(
-                        "Get video insights 🔎", variant="primary", scale=1, rounded=True
+                        "Get audio insights 🔎", variant="primary", scale=1, rounded=True
                     )
                 btn.click(
                     gio.from_audio_input,