Create app.py

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+from transformers import pipeline
+import yt_dlp as youtube_dl
+import os
+os.environ['PATH'] = 'C:\\Program Files (x86)\\ffmpeg-7.0-essentials_build\\bin;' + os.environ['PATH']
+
+# Define the Whisper pipeline
+whisper = pipeline(model="openai/whisper-large-v3")
+
+def download_youtube_audio(youtube_url):
+    # Options for yt-dlp
+    ydl_opts = {
+    'format': 'bestaudio/best',
+    'postprocessors': [{
+        'key': 'FFmpegExtractAudio',
+        'preferredcodec': 'mp3',
+        'preferredquality': '192',
+    }],
+    'ffmpeg_location': 'C:\\Program Files (x86)\\ffmpeg-7.0-essentials_build\\bin',  # Add this line
+    'outtmpl': 'downloaded_audio.%(ext)s',
+    'noplaylist': True,
+}
+    # Use yt-dlp to download the audio
+    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+        info_dict = ydl.extract_info(youtube_url, download=True)
+        audio_file = ydl.prepare_filename(info_dict)
+        # Replace the extension with 'mp3' since we know we're extracting to mp3
+        audio_file = os.path.splitext(audio_file)[0] + '.mp3'
+
+    return audio_file
+
+def transcribe(audio_file_path, task):
+    if task == "transcribe":
+        # Load the audio file and run it through the Whisper model
+        transcription = whisper(audio_file_path)
+        # Cleanup downloaded audio after transcription
+        os.remove(audio_file_path)
+        return transcription["text"]
+    else:
+        # Assuming you would have a translation function or model
+        pass  # Replace with your translation logic
+
+with gr.Blocks() as demo:
+    with gr.Tab("YouTube"):
+        with gr.Group():
+            youtube_url = gr.Textbox(placeholder="Paste the URL to a YouTube video here")
+            task = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe")
+            submit_button = gr.Button("Submit")
+        output = gr.Textbox(label="output 1")
+
+    submit_button.click(
+        fn=lambda url, task: transcribe(download_youtube_audio(url), task),
+        inputs=[youtube_url, task],
+        outputs=output
+    )
+
+if __name__ == "__main__":
+    demo.launch(share=True)