Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import moviepy.editor as mp
 import librosa
+import numpy as np
 from transformers import pipeline
 from concurrent.futures import ThreadPoolExecutor
 
@@ -39,17 +40,13 @@ def generate_subtitles(video_file, language_name):
         
         print(f"Processing video from path: {video_path}")
 
-        # Extract audio from video using moviepy
+        # Load the video and extract audio directly
         video = mp.VideoFileClip(video_path)
-        audio_path = "temp_audio.wav"
         audio = video.audio
-        audio.write_audiofile(audio_path, codec='pcm_s16le')
+        waveform, sr = librosa.load(audio.reader, sr=16000)  # Load directly from audio reader
 
         print("Starting speech-to-text transcription")
 
-        # Load the audio file as a waveform using librosa
-        waveform, sr = librosa.load(audio_path, sr=16000)  # sr=16000 for Whisper
-
         # Process audio in chunks
         chunk_duration = 15  # seconds
         chunk_size = sr * chunk_duration  # number of samples per chunk