Update dub.py

dub.py

@@ -3,24 +3,9 @@ import tempfile
 from gtts import gTTS
 from pydub import AudioSegment
 import moviepy.editor as mp
-import speech_recognition as sr
+from pocketsphinx import AudioFile
 from moviepy.editor import VideoFileClip, AudioFileClip
 
-def merge_video_audio(video_file, audio_file, output_file):
-    video_clip = VideoFileClip(video_file)
-    
-    if audio_file is not None:
-        audio_clip = AudioFileClip(audio_file)
-        
-        if audio_clip.duration < video_clip.duration:
-            audio_clip = audio_clip.set_duration(video_clip.duration)
-        else:
-            audio_clip = audio_clip.subclip(0, video_clip.duration)
-
-        video_clip = video_clip.set_audio(audio_clip)
-
-    video_clip.write_videofile(output_file, codec="libx264", audio_codec="aac", verbose=False)
-    
 def text_to_speech(text, lang='es'):
     tts = gTTS(text=text, lang=lang, slow=False)
     with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_file:
@@ -30,17 +15,17 @@ def text_to_speech(text, lang='es'):
 def transcribe_and_dub(video_file):
     temp_folder = tempfile.mkdtemp()
 
-    recognizer = sr.Recognizer()
-
     try:
         with mp.VideoFileClip(video_file) as video:
             audio_file = os.path.join(temp_folder, "audio.wav")
             video.audio.write_audiofile(audio_file)
 
-        with sr.AudioFile(audio_file) as source:
-            audio = recognizer.record(source)
+        audio_transcription = []
 
-        text = recognizer.recognize_google(audio, language='es')
+        with AudioFile(audio_file) as source:
+            audio_transcription = source.hypothesize()
+
+        text = " ".join(audio_transcription)
         print(f"Texto reconocido: {text}")
 
         dubbed_audio_file = text_to_speech(text)
@@ -62,3 +47,18 @@ def transcribe_and_dub(video_file):
     except Exception as e:
         print(f"Error durante la transcripción y el doblaje: {str(e)}")
         return None
+
+def merge_video_audio(video_file, audio_file, output_file):
+    video_clip = VideoFileClip(video_file)
+    
+    if audio_file is not None:
+        audio_clip = AudioFileClip(audio_file)
+        
+        if audio_clip.duration < video_clip.duration:
+            audio_clip = audio_clip.set_duration(video_clip.duration)
+        else:
+            audio_clip = audio_clip.subclip(0, video_clip.duration)
+
+        video_clip = video_clip.set_audio(audio_clip)
+
+    video_clip.write_videofile(output_file, codec="libx264", audio_codec="aac", verbose=False)