Update README.md

README.md

@@ -245,6 +245,8 @@ model = SALM.from_pretrained('nvidia/canary-qwen-2.5b')
 
 Input to Canary-Qwen-2.5B is a batch of prompts that include audio.
 
+Example usage in ASR mode (speech-to-text):
+
 ```python
 answer_ids = model.generate(
     prompts=[
@@ -255,6 +257,18 @@ answer_ids = model.generate(
 print(model.tokenizer.ids_to_text(answer_ids[0].cpu()))
 ```
 
+Example usage in LLM mode (text-only):
+
+```python
+prompt = "..."
+transcript = "..."
+with model.llm.disable_adapter():
+    answer_ids = model.generate(
+        prompts=[[{"role": "user", "content": f"{prompt}\n\n{transcript}"}]],
+        max_new_tokens=2048,
+    )
+```
+
 To transcribe a dataset of recordings, specify the input as jsonl manifest file, where each line in the file is a dictionary containing the following fields: 
 
 ```yaml