Update app.py

app.py

@@ -2,15 +2,16 @@ import gradio as gr
 import numpy as np
 import librosa
 import cv2
-import moviepy.editor as mp
+import ffmpeg
 import speech_recognition as sr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import tensorflow as tf
 from tensorflow.keras.preprocessing.text import tokenizer_from_json
 from tensorflow.keras.models import load_model
 from tensorflow.keras.preprocessing.sequence import pad_sequences
-from tensorflow.keras.preprocessing.image import img_to_array, load_img
+from tensorflow.keras.preprocessing.image import img_to_array
 from collections import Counter
+import os
 
 # Load necessary models and files
 text_model = load_model('model_for_text_emotion_updated(1).keras')  # Load your text emotion model
@@ -73,12 +74,13 @@ def process_video(video_path):
     most_common_emotion = Counter(predictions).most_common(1)[0][0]
     return emotion_mapping[most_common_emotion]
 
-# Extract audio from video and process
+# Extract audio from video using ffmpeg-python
 def extract_audio_from_video(video_path):
-    video = mp.VideoFileClip(video_path)
-    audio = video.audio
     audio_file = 'audio.wav'
-    audio.write_audiofile(audio_file)
+    (ffmpeg
+        .input(video_path)
+        .output(audio_file, format='wav', acodec='pcm_s16le')
+        .run(overwrite_output=True))
     return audio_file
 
 def transcribe_audio(audio_file):