Update main.py

main.py

@@ -99,7 +99,8 @@ def decode_audio(tokens, quantizer, pad_tokens, n_original_tokens):
 
 # Inference functions
 def infer_text_to_audio(text, model, tokenizer, quantizer, max_seq_length=1024, top_k=20):
-    text_tokenized = tokenizer(text, return_tensors="pt")
+    print(text)
+    text_tokenized = tokenizer(str(text), return_tensors="pt")
     text_input_tokens = text_tokenized["input_ids"].to(device)
 
     soa = tokenizer(start_audio_token, return_tensors="pt")["input_ids"][:, -1:].to(device)