Update app.py

app.py

@@ -30,6 +30,7 @@ class GradioInference():
         if size != self.current_size:
             self.loaded_model = whisper.load_model(size)
             self.current_size = size
+        
         results = self.loaded_model.transcribe(path, language=lang)
 
         # Perform summarization on the transcription
@@ -52,10 +53,30 @@ class GradioInference():
         return self.yt.thumbnail_url, self.yt.title
 
 
-def transcribe_audio(audio_file):
-    model = whisper.load_model("base")
-    result = model.transcribe(audio_file)
-    return result["text"]
+    def from_audio_input(self, lang, size, audio_file):
+        if lang == "none":
+            lang = None
+        
+        if size != self.current_size:
+            self.loaded_model = whisper.load_model(size)
+            self.current_size = size
+
+        results = self.loaded_model.transcribe(audio_file, language=lang)
+
+        # Perform summarization on the transcription
+        transcription_summary = self.summarizer(results["text"], max_length=130, min_length=30, do_sample=False)
+
+        # Extract keywords using VoiceLabT5
+        task_prefix = "Keywords: "
+        input_sequence = task_prefix + results["text"]
+        input_ids = self.keyword_tokenizer(input_sequence, return_tensors="pt", truncation=False).input_ids
+        output = self.keyword_model.generate(input_ids, no_repeat_ngram_size=3, num_beams=4)
+        predicted = self.keyword_tokenizer.decode(output[0], skip_special_tokens=True)
+        keywords = [x.strip() for x in predicted.split(',') if x.strip()]
+
+        label = self.classifier(results["text"])[0]["label"]
+        
+        return results["text"], transcription_summary[0]["summary_text"], keywords, label
 
 
 gio = GradioInference()
@@ -82,14 +103,14 @@ with block as demo:
                 with gr.Row().style(equal_height=True):
                     size = gr.Dropdown(label="Model Size", choices=gio.sizes, value='base')
                     lang = gr.Dropdown(label="Language (Optional)", choices=gio.langs, value="none")
-                link = gr.Textbox(label="YouTube Link")
+                link = gr.Textbox(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")
-                    text = gr.Textbox(label="Transcription", placeholder="Transcription Output", lines=10).style(show_copy_button=True, container=True)
+                    text = gr.Textbox(label="Transcription", 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).style(show_copy_button=True, container=True)
-                    keywords = gr.Textbox(label="Keywords", placeholder="Keywords Output", lines=5).style(show_copy_button=True, container=True)
+                    summary = gr.Textbox(label="Summary", placeholder="Summary Output...", lines=5).style(show_copy_button=True, container=True)
+                    keywords = gr.Textbox(label="Keywords", placeholder="Keywords Output...", lines=5).style(show_copy_button=True, container=True)
                     label = gr.Label(label="Sentiment Analysis")
                 with gr.Row().style(equal_height=True):
                     clear = gr.ClearButton([link, title, img, text, summary, keywords, label], scale=1)
@@ -104,16 +125,16 @@ with block as demo:
                     lang = gr.Dropdown(label="Language (Optional)", choices=gio.langs, value="none")
                 audio_file = gr.Audio(type="filepath")
                 with gr.Row().style(equal_height=True):
-                    # img = gr.Image(label="Thumbnail")
-                    text = gr.Textbox(label="Transcription", placeholder="Transcription Output", lines=10).style(show_copy_button=True, container=False)
+                    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)
-                #     keywords = gr.Textbox(label="Keywords", placeholder="Keywords Output", lines=5)
+                    summary = gr.Textbox(label="Summary", placeholder="Summary Output", lines=5)
+                    keywords = gr.Textbox(label="Keywords", placeholder="Keywords Output", lines=5)
+                    label = gr.Label(label="Sentiment Analysis")
                 with gr.Row().style(equal_height=True):
                     clear = gr.ClearButton([text], scale=1)
                     btn = gr.Button("Get video insights", variant='primary', scale=1)  # Updated button label
-                btn.click(transcribe_audio, inputs=[audio_file], outputs=[text])
-                # link.change(gio.populate_metadata, inputs=[link], outputs=[img, title])
+                btn.click(gio.from_audio_input, inputs=[lang, size, audio_file], outputs=[text, summary, keywords, label])
+                
 
 with block:
     gr.Markdown("About the app:")