Update app.py

app.py

@@ -1,45 +1,36 @@
 import gradio as gr
-import os
-import torch
-import gc
-from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
-import tempfile
 import yt_dlp
+import whisper
+import tempfile
 
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-asr_pipeline = pipeline("automatic-speech-recognition", model="openai/whisper-base")
-
-def download_audio(url: str, temp_dir: str) -> str:
-    output_path = os.path.join(temp_dir, "audio.%(ext)s")
-    ydl_opts = {
-        'format': 'bestaudio/best',
-        'outtmpl': output_path,
-        'quiet': True,
-        'postprocessors': [{
-            'key': 'FFmpegExtractAudio',
-            'preferredcodec': 'mp3',
-            'preferredquality': '192',
-        }],
-    }
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-        ydl.download([url])
-    return output_path.replace('%(ext)s', 'mp3')
+def download_audio(url, cookies_path):
+    with tempfile.NamedTemporaryFile(suffix='.mp3', delete=False) as tmpfile:
+        ydl_opts = {
+            'format': 'bestaudio/best',
+            'outtmpl': tmpfile.name,
+            'quiet': True,
+            'cookiefile': cookies_path,
+            'postprocessors': [{
+                'key': 'FFmpegExtractAudio',
+                'preferredcodec': 'mp3',
+                'preferredquality': '192',
+            }]
+        }
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([url])
+        return tmpfile.name
 
-def process_video(url: str) -> str:
-    with tempfile.TemporaryDirectory() as tmpdir:
-        audio_path = download_audio(url, tmpdir)
-        transcription_result = asr_pipeline(audio_path)
-        text = transcription_result['text']
-        if len(text.strip()) < 50:
-            return "Transcription too short or unclear"
-        gc.collect()
-        if torch.cuda.is_available():
-            torch.cuda.empty_cache()
-        summary_result = summarizer(text, max_length=150, min_length=50, do_sample=False)
-        return summary_result[0]['summary_text']
+def process_video(url, cookies_path):
+    audio_file = download_audio(url, cookies_path)
+    model = whisper.load_model("base")
+    result = model.transcribe(audio_file)
+    return result['text']
 
 def main(url):
-    return process_video(url)
+    cookies_path = 'cookies.txt'  # Provide path to your exported cookies file
+    transcript = process_video(url, cookies_path)
+    return transcript
+
+demo = gr.Interface(fn=main, inputs=gr.Textbox(label="YouTube URL"), outputs="text")
 
-iface = gr.Interface(fn=main, inputs="text", outputs="text", title="YouTube Audio Summarizer")
-iface.launch()
+demo.launch()