Update app.py

app.py

@@ -26,6 +26,25 @@ DUPLICATE = """
 
 IMAGE_WIDTH = 512
 
+def extract_text_from(vid_link):
+  video_url = vid_link
+  yt = YouTube(video_url)
+  text = ""
+  audio_stream = yt.streams.get_audio_only()
+  audio_stream.download(filename='tmp.mp4')
+  audio_clip = AudioFileClip('tmp.mp4')
+  audio_clip.write_audiofile('tmp.wav')
+  r = sr.Recognizer()
+  with sr.AudioFile('tmp.wav') as source:
+    audio_data = r.record(source)
+    try:
+        text = r.recognize_google(audio_data,  language='ar')
+    except sr.UnknownValueError:
+        print("Google Speech Recognition could not understand audio")
+    except sr.RequestError as e:
+        print("Could not request results from Google Speech Recognition service; {0}".format(e))
+    return text
+      
 
 def preprocess_stop_sequences(stop_sequences: str) -> Optional[List[str]]:
     if not stop_sequences:
@@ -40,7 +59,7 @@ def preprocess_image(image: Image.Image) -> Optional[Image.Image]:
 
 def user(text_prompt: str, chatbot: List[Tuple[str, str]]):
     return "", chatbot + [[text_prompt, None]]
-
+#https://www.youtube.com/watch?v=5Abk7EU5EJI
 
 def bot(
     google_key: str,
@@ -58,7 +77,8 @@ def bot(
             "GOOGLE_API_KEY is not set. "
             "Please follow the instructions in the README to set it up.")
 
-    text_prompt = chatbot[-1][0]
+    #text_prompt = chatbot[-1][0]
+    text_prompt = extract_text_from("https://www.youtube.com/watch?v=5Abk7EU5EJI")
     genai.configure(api_key=google_key)
     generation_config = genai.types.GenerationConfig(
         temperature=temperature,