Update app.py

app.py

@@ -167,6 +167,7 @@ import torch
 
 import gradio as gr
 import yt_dlp as youtube_dl
+import pytube as pt
 from transformers import pipeline
 from transformers.pipelines.audio_utils import ffmpeg_read
 
@@ -206,7 +207,7 @@ def _return_yt_html_embed(yt_url):
     return HTML_str
 
 def download_yt_audio(yt_url, filename):
-    info_loader = youtube_dl.YoutubeDL()
+    # info_loader = youtube_dl.YoutubeDL()
     
     # try:
     #     info = info_loader.extract_info(yt_url, download=False)
@@ -228,20 +229,24 @@ def download_yt_audio(yt_url, filename):
     #     file_length_hms = time.strftime("%HH:%MM:%SS", time.gmtime(file_length_s))
     #     raise gr.Error(f"Maximum YouTube length is {yt_length_limit_hms}, got {file_length_hms} YouTube video.")
     
-    ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
+    # ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
     
-    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
-        try:
-            ydl.download([yt_url])
-        except youtube_dl.utils.ExtractorError as err:
-            raise gr.Error(str(err))
+    # with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+    #     try:
+    #         ydl.download([yt_url])
+    #     except youtube_dl.utils.ExtractorError as err:
+    #         raise gr.Error(str(err))
+    yt = pt.YouTube(yt_url)
+    stream = yt.streams.filter(only_audio=True)[0]
+    stream.download(filename=filename)
 
 @spaces.GPU
 def yt_transcribe(yt_url, task="transcribe", max_filesize=75.0):
     html_embed_str = _return_yt_html_embed(yt_url)
 
     with tempfile.TemporaryDirectory() as tmpdirname:
-        filepath = os.path.join(tmpdirname, "video.mp4")
+        # filepath = os.path.join(tmpdirname, "video.mp4")
+        filepath = os.path.join(tmpdirname, "audio.mp3")
         download_yt_audio(yt_url, filepath)
         with open(filepath, "rb") as f:
             inputs = f.read()