Update app.py

app.py

@@ -1,10 +1,6 @@
 import gradio as gr
 from gradio.inputs import Textbox
 
-import nltk
-nltk.download('punkt')
-from nltk.tokenize import sent_tokenize, word_tokenize
-
 import re
 from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5HifiGan
 from datasets import load_dataset
@@ -57,18 +53,8 @@ def generateAudio(text_to_audio, s3_save_as):
     
         # Remove line breaks
         text = re.sub(r"\n", " ", text)
-    
-        sentences = sent_tokenize(text)
-        tokens = []
-        for sentence in sentences:
-            tokens.extend(word_tokenize(sentence))
-    
-        if len(tokens) <= max_tokens:
-            return text
-    
-        cut_tokens = tokens[:max_tokens]
-        cut = ' '.join(cut_tokens)
-        return cut
+
+        return text
 
     def save_audio_to_s3(audio):
         # Create an instance of the S3 client
@@ -86,8 +72,9 @@ def generateAudio(text_to_audio, s3_save_as):
         # Preprocess text and recortar
         text = cut_text(text, max_tokens=500)
         
-        # Divide el texto en segmentos de 100 caracteres
-        segmentos = [text[i:i+100] for i in range(0, len(text), 100)]
+        # Divide el texto en segmentos de 30 palabras
+        palabras = text.split()
+        segmentos = [' '.join(palabras[i:i+30]) for i in range(0, len(palabras), 30)]
         
         # Generar audio para cada segmento y combinarlos
         audio_segments = []
@@ -106,10 +93,11 @@ def generateAudio(text_to_audio, s3_save_as):
         audio_buffer = BytesIO()
         sf.write(audio_buffer, combined_audio.cpu().numpy(), samplerate=16000, format='WAV')
         audio_buffer.seek(0)
-
+        
         # Guardar el audio combinado en S3
         save_audio_to_s3(audio_buffer)
-
+    
+    
     save_text_to_speech(text_to_audio, 2271)
     return s3_save_as