Update app.py

app.py

@@ -9,7 +9,7 @@ import numpy as np
 
 # Initialize Whisper model
 try:
-    whisper_model = whisper.load_model("base")  # Ensure the model is installed from the correct Whisper library
+    whisper_model = whisper.load_model("base")
 except Exception as e:
     st.error(f"Error loading Whisper model: {e}")
 
@@ -55,12 +55,31 @@ if video_file:
 
             for start in np.arange(0, audio_duration, chunk_length):
                 end = min(start + chunk_length, audio_duration)
-                segment = audio_clip[int(start * whisper.audio.SAMPLE_RATE):int(end * whisper.audio.SAMPLE_RATE)]  # Convert to the right format
+                segment = audio_clip[int(start * whisper.audio.SAMPLE_RATE):int(end * whisper.audio.SAMPLE_RATE)]
                 result = model.transcribe(segment)
                 segments.append(result['text'])
 
             return ' '.join(segments)
 
+        # Function to translate text in chunks
+        def translate_in_chunks(text, translator, max_length=500):
+            words = text.split()
+            chunks = []
+            current_chunk = ""
+
+            for word in words:
+                if len(current_chunk) + len(word) + 1 <= max_length:
+                    current_chunk += " " + word if current_chunk else word
+                else:
+                    chunks.append(current_chunk)
+                    current_chunk = word
+
+            if current_chunk:
+                chunks.append(current_chunk)
+
+            translated_chunks = [translator.translate(chunk) for chunk in chunks]
+            return ' '.join(translated_chunks)
+
         # Transcribe audio using Whisper
         try:
             original_text = transcribe_audio_in_chunks(audio_path, whisper_model)
@@ -68,7 +87,7 @@ if video_file:
 
             # Translate text to the target language
             translator = Translator(to_lang=LANGUAGES[target_language])
-            translated_text = translator.translate(original_text)
+            translated_text = translate_in_chunks(original_text, translator)
             st.write(f"Translated Text ({target_language}):", translated_text)
 
             # Convert translated text to speech