Update README.md

README.md

@@ -37,7 +37,7 @@ Install it using:
 ```bash
 pip install snac
 ```
-To encode (and reconstruct) audio with SNAC in Python, use the following code:
+To encode (and decode) audio with SNAC in Python, use the following code:
 
 ```python
 import torch
@@ -47,7 +47,15 @@ model = SNAC.from_pretrained("hubertsiuzdak/snac_44khz").eval().cuda()
 audio = torch.randn(1, 1, 44100).cuda()  # B, 1, T
 
 with torch.inference_mode():
-    audio_hat, _, codes, _, _ = model(audio)
+    codes = model.encode(audio)
+    audio_hat = model.decode(codes)
+```
+
+You can also encode and reconstruct in a single call:
+
+```python
+with torch.inference_mode():
+    audio_hat, codes = model(audio)
 ```
 
 ⚠️ Note that `codes` is a list of token sequences of variable lengths, each corresponding to a different temporal