Update app.py

app.py

@@ -1,19 +1,43 @@
+# def translate_and_speak(text):
+#     input_text = "en " + text
+#     encoded = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True).to(device)
+#     generated_tokens = model.generate(**encoded, max_length=128, num_beams=5, early_stopping=True)
+#     output = tokenizer.decode(generated_tokens[0], skip_special_tokens=True)
+
+#     for tag in ["__en__", "__sa__", "en", "sa"]:
+#         output = output.replace(tag, "")
+#     sanskrit_text = output.strip()
+
+#     # Convert to speech
+#     tts = gTTS(sanskrit_text, lang='hi')
+#     with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as fp:
+#         tts.save(fp.name)
+#         audio_path = fp.name
+
+#     return sanskrit_text, audio_path
 from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
 import torch
 from gtts import gTTS
 import gradio as gr
 import tempfile
 
+
+
 # Load model and tokenizer
-model_name = "SweUmaVarsh/m2m100-en-sa-translation"
 model__name = "Helsinki-NLP/opus-mt-en-hi"
-tokenizer = M2M100Tokenizer.from_pretrained(model_name)
-model = M2M100ForConditionalGeneration.from_pretrained(model_name)
+
 
 # Use GPU if available
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model = model.to(device)
 
+
+model_name = "SweUmaVarsh/m2m100-en-sa-translation"
+tokenizer = M2M100Tokenizer.from_pretrained(model_name)
+model = M2M100ForConditionalGeneration.from_pretrained(model_name)
+
+
+
 def translate_and_speak(text):
     input_text = "en " + text
     encoded = tokenizer(input_text, return_tensors="pt", truncation=True, padding=True).to(device)