docs: link tested any-to-any pipeline and state ASR task boundary

Signed-off-by: LauraGPT <18321252+LauraGPT@users.noreply.github.com>

README.md

@@ -103,6 +103,19 @@ Hotwords are hints, not an enforced vocabulary. In the paired Chinese sample che
 
 `language` accepts Chinese, English, and Japanese as ISO codes, full English names, or the checkpoint Chinese names (`中文`, `英文`, `日文`). Keep batch inputs and decoded outputs in order; use `processor_kwargs={"text_kwargs": {"padding": True}}` together with the other processor options for different-length batches. Reject empty batches before calling the processor. An upstream `IndexError` for `audio=[]` was observed in the historical `fc501` source environment; that observation is not a new 5.17.0 test result.
 
+## Using the pipeline API
+
+Use the explicitly selected `any-to-any` task with structured audio/language
+messages: the [runnable pipeline example](https://github.com/QwenAudio/Fun-ASR/tree/main/examples/transformers#use-the-transformers-pipeline-api)
+was executed on Transformers 5.17.0, torch 2.10.0+cpu and the pinned public English
+sample. It returns transcription text without the input conversation.
+
+The standard `automatic-speech-recognition` pipeline is a different processing
+route: our 5.17.0 test fails with a floating-point token-index error for this
+checkpoint. Do not substitute that task or rely on automatic task inference.
+This pipeline check is CPU single-file only, not GPU/batch, accuracy or capacity
+validation. The native processor/generate quickstart above remains supported.
+
 ## CUDA with the canonical CLI
 
 The [isolated CUDA recipe](https://github.com/QwenAudio/Fun-ASR/tree/main/examples/transformers#cuda-an-isolated-tested-recipe)