Add Pipeline usage snippet to Transformers section

README.md

@@ -422,6 +422,20 @@ Until Nemotron3_5Asr is part of an official Transformers release, install Transf
 pip install git+https://github.com/huggingface/transformers
 ```
 
+<details>
+  <summary>➡️ Pipeline</summary>
+
+```python
+from transformers import pipeline
+
+pipe = pipeline("automatic-speech-recognition", model="nvidia/nemotron-3.5-asr-streaming-0.6b")
+out = pipe("https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3")
+print(out)
+```
+
+The pipeline uses the default language prompt (index 0, `en-US`). For explicit language conditioning or automatic detection, pass the processor's `language` argument (see the AutoModel example below).
+</details>
+
 <details>
   <summary>➡️ Offline transcription</summary>