Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import moviepy.editor as mp
 import librosa
-import numpy as np
 from transformers import pipeline
 
 # Load Whisper model for speech-to-text
@@ -46,11 +45,8 @@ def generate_subtitles(video_file, language_name):
         # Load the audio file as a waveform using librosa
         waveform, sr = librosa.load(audio_path, sr=16000)  # sr=16000 for Whisper
 
-        # Convert the waveform (numpy array) to a list of floats (required by Whisper)
-        waveform_list = waveform.tolist()
-
-        # Pass the waveform to Whisper's ASR model
-        transcription = asr(waveform_list)["text"]
+        # Pass the waveform (NumPy array) directly to Whisper's ASR model
+        transcription = asr(waveform)["text"]
 
         print("Starting translation")