Update app.py

app.py

@@ -7,6 +7,8 @@ import scipy
 from gtts import gTTS
 from io import BytesIO
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from transformers import VitsTokenizer, VitsModel
+
 
 def extract_text(pdf_file):
     pdfReader = PyPDF2.PdfReader(pdf_file)
@@ -53,11 +55,21 @@ def summarize_text(text):
     return summary
 
 def text_to_audio(text):
-    tts = gTTS(text, lang='en') 
-    buffer = BytesIO()
-    tts.write_to_fp(buffer)
-    buffer.seek(0)  
-    return buffer.read()
+    #tts = gTTS(text, lang='en') 
+    #buffer = BytesIO()
+    #tts.write_to_fp(buffer)
+    #buffer.seek(0)  
+    #return buffer.read()
+
+    tokenizer = VitsTokenizer.from_pretrained("facebook/mms-tts-eng")
+    model = VitsModel.from_pretrained("facebook/mms-tts-eng")
+
+    inputs = tokenizer([text], return_tensors="pt")
+
+    with torch.no_grad():
+      outputs = model(**inputs)
+  
+    return outputs.waveform[0]
 
 def audio_pdf(pdf_file):
     text = extract_text(pdf_file)