Update app.py

app.py

@@ -6,7 +6,6 @@ import os
 class GradioInference():
   def __init__(self):
     self.sizes = list(whisper._MODELS.keys())
-    self.file = "Upload audio/video"
     self.current_size = "base"
     self.loaded_model = whisper.load_model(self.current_size)
     self.yt = None
@@ -14,37 +13,14 @@ class GradioInference():
   def __call__(self, link, file, size, subs):
     if self.yt is None:
       self.yt = YouTube(link)
-      path = self.yt.streams.filter(only_audio=True)[0].download(filename="tmp.mp4")
-
-    if self.file == None:
-      self.file = path
+    
+    path = self.yt.streams.filter(only_audio=True)[0].download(filename="tmp.mp4")
 
     if size != self.current_size:
       self.loaded_model = whisper.load_model(size)
       self.current_size = size
     results = self.loaded_model.transcribe(path)
 
-    if subs == "None":
-      return results["text"]
-    elif subs == ".srt":
-      return self.srt(results["segments"])
-    elif ".csv" == ".csv":
-      return self.csv(results["segments"])
-   
-  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
-  
-  def csv(self, segments):
-    output = ""
-    for segment in segments:
-      output += f"{segment['start']},{segment['end']},{segment['text']}\n"
-    return output
-
   def format_time(self, time):
     hours = time//3600
     minutes = (time - hours*3600)//60
@@ -79,16 +55,13 @@ with block:
         with gr.Box():
           with gr.Row().style(equal_height=True):
             sz = gr.Dropdown(label="Model Size", choices=gio.sizes, value='base')
-            file = gr.File(label="Upload Video/Audio")
-          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):
             img = gr.Image(label="Thumbnail")
-            text = gr.Textbox(label="Transcription", placeholder="Transcription Output", lines=10)
+         >>>   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, file, sz, wt], outputs=[text])
+          btn.click(gio, inputs=[link, sz, wt], outputs=[text])
           link.change(gio.populate_metadata, inputs=[link], outputs=[img, title])
 block.launch()