Update app.py

app.py

@@ -5,14 +5,27 @@ from pytube import YouTube
 
 
 pipe = pipeline(model="irena/whisper-small-sv-SE") 
+def main_generator(youtube_id:str):
+  YouTubeID = youtube_id.split("https://www.youtube.com/watch?v=") #
+  if len(YouTubeID)>1:
+      YouTubeID = YouTubeID[1]
+  else:
+      YouTubeID ='xOZM-1p-jAk'
+      
+  OutputFile = f'test_audio_youtube_{YouTubeID}.m4a'
+
+  os.system(f"youtube-dl -o {OutputFile} {YouTubeID} --extract-audio --restrict-filenames -f 'bestaudio[ext=m4a]'")
+  
+  result = model_whisper.transcribe(OutputFile)
+  text = result['text']
+
+  output_list = []
+
+      output_list.append(text)
+
+  return text 
 
 
-def yt(link):
-    yt = YouTube(link)
-    stream = yt.streams.filter(only_audio=True)[0]
-    stream.download(filename="audio.mp3")
-    text = pipe("audio.mp3")["text"]
-    return text
 
 def transcribe(audio):
     text = pipe(audio)["text"]
@@ -29,16 +42,38 @@ iface = gr.Interface(
     description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model. An audio for recognize.",
 )
 
-yt = gr.Interface(
-    fn=yt,
-    inputs=[gr.inputs.Textbox(lines=1, label="Youtube URL")],
-    outputs=["html", "text"],
-    title="Whisper Small Swedish-Youtube",
-    description="Realtime demo for Swedish speech recognition using a fine-tuned Whisper small model. A Youtube URL for recognize."
+inputs = [gr.Textbox(lines=1, placeholder="Link of youtube video here...", label="Input")]
+outputs = gr.HighlightedText()
+title="ASR FOR SPANISH MEDICAL RECORDS"
+description = "This demo uses AI Models to create an AUDIO ANNOTATION FOR MEDICAL RECORDS"
+examples = ['https://www.youtube.com/watch?v=xOZM-1p-jAk']
+io = gr.Interface(fn=main_generator, inputs=inputs, outputs=outputs, title=title, description = description, examples = examples,
+
+                  css= """.gr-button-primary { background: -webkit-linear-gradient( 
+                    90deg, #355764 0%, #55a8a1 100% ) !important;     background: #355764;
+                        background: linear-gradient( 
+                    90deg, #355764 0%, #55a8a1 100% ) !important;
+                        background: -moz-linear-gradient( 90deg, #355764 0%, #55a8a1 100% ) !important;
+                        background: -webkit-linear-gradient( 
+                    90deg, #355764 0%, #55a8a1 100% ) !important;
+                    color:white !important}"""
+                  )
 
-)
 
 with demo:
     gr.TabbedInterface([iface, yt], ["Transcribe Audio", "Transcribe YouTube"])
 
-demo.launch(enable_queue=True)
+demo.launch(enable_queue=True)
+
+
+
+
+
+
+
+
+
+
+
+
+