Update app.py

app.py

@@ -1,6 +1,8 @@
 import streamlit as st
 from faster_whisper import WhisperModel
 import logging
+import tempfile
+import os
 
 # Configure logging for debugging purposes
 logging.basicConfig()
@@ -15,13 +17,21 @@ def format_timestamp(seconds):
 
 def transcribe(audio_file, model_size):
     # Initialize the Whisper model based on the selected model size
-    device = "cpu"  # GPU : cuda  CPU : cpu
-    compute_type = "int8"  # GPU : float16 or int8 - CPU : int8
+    device = "cpu"  # Use "cpu" for CPU, "cuda" for GPU
+    compute_type = "int8"  # Use "int8" for faster inference on both CPU and GPU
     
     model = WhisperModel(model_size, device=device, compute_type=compute_type)
-    
+
+    # Save the uploaded file to a temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(audio_file.name)[1]) as tmp:
+        tmp.write(audio_file.getvalue())
+        tmp_path = tmp.name
+
     # Transcribe the audio file
-    segments, _ = model.transcribe(audio_file.name, audio_file)
+    segments, _ = model.transcribe(tmp_path)
+    
+    # Clean up the temporary file
+    os.remove(tmp_path)
     
     # Format and gather transcription with enhanced timestamps
     transcription_with_timestamps = [
@@ -31,8 +41,8 @@ def transcribe(audio_file, model_size):
     
     return "\n".join(transcription_with_timestamps)
 
-# Streamlit UI
-st.title("Whisper API")
+# Streamlit UI components
+st.title("Whisper")
 st.write("For API use please visit [this space](https://huggingface.co/spaces/Lenylvt/Whisper-API)")
 
 audio_file = st.file_uploader("🎵 Upload Audio or Video", type=['wav', 'mp3', 'ogg', 'mp4', 'avi'])