Update README.md

README.md

@@ -41,7 +41,46 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-[More Information Needed]
+```python
+
+from datasets import load_dataset
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
+
+repo_id = "MERaLiON/AudioLLM"
+
+processor = AutoProcessor.from_pretrained(
+    repo_id, 
+    trust_remote_code=True,
+    )
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    repo_id,
+    use_safetensors=True,
+    trust_remote_code=True,
+)
+
+prompt = "Can you please turn this audio into text format?"
+conversation = [
+    {
+        "role": "user",
+        "content": f"Given the following audio context: <SpeechHere>\n\nText instruction: {prompt}"
+    }
+]
+chat_prompt = processor.tokenizer.apply_chat_template(
+    conversation=conversation,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+libri_data = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
+audio_array = libri_data[0]["audio"]["array"]
+
+inputs = processor(text=chat_prompt, audios=audio_array, time_duration_limit=20)
+
+outputs = model.generate(**inputs, max_new_tokens=128)
+
+print(processor.decode(outputs[0, inputs['input_ids'].size(1):], skip_special_tokens=True))
+
+```
 
 ### Downstream Use [optional]