Add a usage example to the model card

README.md

@@ -10,4 +10,19 @@ datasets:
 - slseanwu/clotho-chatgpt-mixup-50K
 - audiocaps
 license: cc-by-4.0
----
+---
+
+## Usage
+
+```python
+import librosa
+from espnet2.bin.asr_inference import Speech2Text
+
+speech2text = Speech2Text.from_pretrained(model_tag="espnet/DCASE23.AudioCaptioning.PreTrained")
+# librosa resamples and mixes to one channel, so any file works; 16000 is
+# what nearly every espnet recogniser is trained on - check this model's
+# config if its audio is not 16 kHz
+speech, rate = librosa.load("audio.wav", sr=16000, mono=True)
+text, *_ = speech2text(speech)[0]
+print(text)
+```