app.py

app.py

@@ -0,0 +1,52 @@
+import os
+import gradio as gr
+import whisper
+import subprocess
+
+# Install FFmpeg (required for audio extraction)
+os.system("apt update && apt install -y ffmpeg")
+
+# Load Whisper Model
+model = whisper.load_model("base")  # Change to "tiny", "small", etc. for performance
+
+def process_video(video_file):
+    """
+    Extracts audio from the uploaded video, transcribes it using Whisper, and returns the text.
+    """
+    try:
+        # Define File Paths
+        video_path = video_file.name
+        audio_file = "extracted_audio.wav"
+        transcription_file = "transcription.txt"
+
+        # Extract Audio Using FFmpeg
+        command = f"ffmpeg -i {video_path} -vn -acodec pcm_s16le -ar 16000 -ac 1 {audio_file}"
+        subprocess.run(command, shell=True, check=True)
+
+        # Transcribe Audio
+        result = model.transcribe(audio_file)
+
+        # Save Transcription to a Text File
+        with open(transcription_file, "w", encoding="utf-8") as f:
+            f.write(result["text"])
+
+        return result["text"], transcription_file
+
+    except Exception as e:
+        return f"❌ Error: {e}", None
+
+# Gradio Interface
+with gr.Blocks() as app:
+    gr.Markdown("# 🎙 Video to Text Transcription using Whisper")
+    gr.Markdown("Upload a video file, and the AI will transcribe the speech into text.")
+    
+    video_input = gr.File(label="Upload Video File")
+    transcribed_text = gr.Textbox(label="Transcription", lines=10)
+    download_button = gr.File(label="Download Transcription")
+
+    btn = gr.Button("Transcribe")
+
+    btn.click(fn=process_video, inputs=video_input, outputs=[transcribed_text, download_button])
+
+# Launch the Gradio App
+app.launch()