Update dub.py

dub.py

@@ -3,13 +3,13 @@ import tempfile
 from gtts import gTTS
 from pydub import AudioSegment
 import moviepy.editor as mp
-import speech_recognition as sr
+from pocketsphinx import AudioFile
 
 def merge_video_audio(video_file, audio_file, output_file):
     video_clip = mp.VideoFileClip(video_file)
     
     if audio_file is not None:
-        audio_clip = mp.AudioFileClip(audio_file)
+        audio_clip = AudioSegment.from_wav(audio_file)
         
         if audio_clip.duration < video_clip.duration:
             audio_clip = audio_clip.set_duration(video_clip.duration)
@@ -32,20 +32,20 @@ def transcribe_and_dub(video_file):
     try:
         with mp.VideoFileClip(video_file) as video:
             audio_file = os.path.join(temp_folder, "audio.wav")
-            video.audio.write_audiofile(audio_file)
+            video.audio.write_audiofile(audio_file, codec='pcm_s16le')
 
-        recognizer = sr.Recognizer()
+        audio_transcription = []
 
-        with sr.AudioFile(audio_file) as source:
-            audio = recognizer.record(source)
+        with AudioFile(audio_file) as source:
+            audio_transcription = source.hypothesize()
 
-        text = recognizer.recognize_google(audio, language='es')
+        text = " ".join(audio_transcription)
         print(f"Texto reconocido: {text}")
 
         dubbed_audio_file = text_to_speech(text)
         print(f"Archivo de audio doblado: {dubbed_audio_file}")
 
-        original_audio = AudioSegment.from_file(audio_file, format="wav")
+        original_audio = AudioSegment.from_wav(audio_file)
         dubbed_audio = AudioSegment.from_mp3(dubbed_audio_file)
 
         final_audio = original_audio.overlay(dubbed_audio)
@@ -60,4 +60,4 @@ def transcribe_and_dub(video_file):
 
     except Exception as e:
         print(f"Error durante la transcripción y el doblaje: {str(e)}")
-        return None
+        return None