Create app.py

app.py

@@ -0,0 +1,62 @@
+import yt_dlp
+import whisper
+from pydub import AudioSegment
+import os
+import time
+
+# Function to download audio from YouTube video
+def download_audio_from_youtube(url):
+    ydl_opts = {
+        'format': 'bestaudio/best',
+        'outtmpl': 'video.%(ext)s',
+        'postprocessors': [{
+            'key': 'FFmpegExtractAudio',
+            'preferredcodec': 'mp3',
+            'preferredquality': '192',
+        }],
+    }
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        ydl.download([url])
+    return 'video.mp3'
+
+# Function to split audio into chunks
+def split_audio(file_path, chunk_length_ms=60000):
+    audio = AudioSegment.from_file(file_path)
+    chunks = [audio[i:i + chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)]
+    chunk_files = []
+    for i, chunk in enumerate(chunks):
+        chunk_file = f"chunk_{i}.mp3"
+        chunk.export(chunk_file, format="mp3")
+        chunk_files.append(chunk_file)
+    return chunk_files
+
+# Function to convert audio to text using Whisper model
+def transcribe_audio(file_path):
+    model = whisper.load_model("small")
+
+    result = model.transcribe(file_path)
+    return result["text"]
+
+# Example usage
+# video_url = "https://youtu.be/x6KuoHihktM?si=VoqHMP8emTnXKJHa"
+video_url=input()
+
+# Step 1: Download audio from YouTube
+print(f"Downloading audio from URL: {video_url}")
+audio_path = download_audio_from_youtube(video_url)
+
+# Step 2: Split the audio into chunks
+print(f"Splitting audio into chunks from path: {audio_path}")
+chunk_files = split_audio(audio_path)
+
+# Step 3: Transcribe each chunk and combine results
+print("Transcribing audio chunks...")
+transcriptions = []
+for chunk_file in chunk_files:
+    print(f"Transcribing chunk: {chunk_file}")
+    transcriptions.append(transcribe_audio(chunk_file))
+    os.remove(chunk_file)  # Clean up chunk file after transcription
+    time.sleep(1)  # Introduce a delay to avoid rate limiting
+
+transcribed_text = " ".join(transcriptions)
+print(f"Transcribed text: {transcribed_text}")