Update app.py

app.py

@@ -13,6 +13,7 @@ from sklearn.cluster import AgglomerativeClustering
 from sklearn.metrics import silhouette_score
 
 from pytube import YouTube
+import yt_dlp
 import torch
 import pyannote.audio
 from pyannote.audio.pipelines.speaker_verification import PretrainedSpeakerEmbedding
@@ -174,21 +175,43 @@ def _return_yt_html_embed(yt_url):
     return HTML_str
 
 def yt_transcribe(yt_url):
-    yt = YouTube(yt_url)
-    html_embed_str = _return_yt_html_embed(yt_url)
-    stream = yt.streams.filter(only_audio=True)[0]
-    stream.download(filename="audio.mp3")
-
+    # yt = YouTube(yt_url)
+    # html_embed_str = _return_yt_html_embed(yt_url)
+    # stream = yt.streams.filter(only_audio=True)[0]
+    # stream.download(filename="audio.mp3")
+
+    ydl_opts = {
+        'format': 'bestvideo*+bestaudio/best',
+        'postprocessors': [{
+            'key': 'FFmpegExtractAudio',
+            'preferredcodec': 'mp3',
+            'preferredquality': '192',
+        }],
+        'outtmpl':'audio.%(ext)s',
+    }
+    
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        ydl.download([yt_url])
+        
     text = pipe("audio.mp3")["text"]
-
     return html_embed_str, text
 
 def convert_time(secs):
     return datetime.timedelta(seconds=round(secs))
 
 def get_youtube(video_url):
-    yt = YouTube(video_url)
-    abs_video_path = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first().download()
+    # yt = YouTube(video_url)
+    # abs_video_path = yt.streams.filter(progressive=True, file_extension='mp4').order_by('resolution').desc().first().download()
+    
+    ydl_opts = {
+      'format': 'bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best',
+    }
+    
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        info = ydl.extract_info(URL, download=False)
+        abs_video_path = ydl.prepare_filename(info)
+        ydl.process_info(info) 
+        
     print("Success download video")
     print(abs_video_path)
     return abs_video_path