Update README.md

README.md

@@ -61,7 +61,7 @@ def audio_to_sound_tokens(audio_path, target_bandwidth=1.5, device="cuda"):
     flatten_tokens = torch.stack((audio_code1, audio_code2), dim=1).flatten().tolist()
 
     # Convert to sound tokens
-    result = ''.join(f'<|sound_{num}|>' for num in flatten_tokens)
+    result = ''.join(f'<|sound_{num:04d}|>' for num in flatten_tokens)
     return f'<|sound_start|>{result}<|sound_end|>'
 
 # Usage