Update app.py

app.py

@@ -13,18 +13,27 @@ class GradioInference():
     if self.yt is None:
        self.yt = YouTube(link)
     path = self.yt.streams.filter(only_audio=True).all()
-    voice=path[0].download(filename="tmp.mp4")
-    results_text = self.loaded_model(voice)["text"]
-    return results_text
+    voice=path[0].download()
+    results_text = self.loaded_model(voice)
+    return self.srt(results_text["segments"])
+
+
+  def format_time(self, time):
+    hours = time//3600
+    minutes = (time - hours*3600)//60
+    seconds = time - hours*3600 - minutes*60
+    milliseconds = (time - int(time))*1000
+    return f"{int(hours):02d}:{int(minutes):02d}:{int(seconds):02d},{int(milliseconds):03d}"
+      
+  def srt(self, segments):
+    output = ""
+    for i, segment in enumerate(segments):
+      output += f"{i+1}\n"
+      output += f"{self.format_time(segment['start'])} --> {self.format_time(segment['end'])}\n"
+      output += f"{segment['text']}\n\n"
+    return output
+  
 
-#if url:
- #     video=YouTube(url).streams.filter(only_audio=True).all()
-  #    audio=video[0].download()
-   # text = pipe(audio)["text"]
-    #  return text
-   # if subs == "None":
-   #   return results["text"]
-   
       
   def populate_metadata(self, link):
     self.yt = YouTube(link)
@@ -52,6 +61,7 @@ with block:
     with gr.Group():
         with gr.Box():
           with gr.Row().style(equal_height=True):
+            wt = gr.Radio(["None", ".srt", ".csv"], label="With Timestamps?")
             link = gr.Textbox(label="YouTube Link")
             title = gr.Label(label="Video Title")
           with gr.Row().style(equal_height=True):
@@ -59,6 +69,6 @@ with block:
             text = gr.Textbox(label="Transcription", placeholder="Transcription Output", lines=10)
           with gr.Row().style(equal_height=True): 
               btn = gr.Button("Transcribe")       
-          btn.click(gio, inputs=[link], outputs=[text])
+          btn.click(gio, inputs=[link, wt], outputs=[text])
           link.change(gio.populate_metadata, inputs=[link], outputs=[img, title])
 block.launch()