From 83b2469669d3fe5cd6c91033e95967d86ada78f6 Mon Sep 17 00:00:00 2001
From: Yong Yue <yongyue@microsoft.com>
Date: Tue, 21 Jul 2026 10:05:01 +0800
Subject: [PATCH] recipe(ast-audioset): add CPU fp32 and fp16
 audio-classification recipes

Add verified CPU recipes for MIT/ast-finetuned-audioset-10-10-0.4593
(Audio Spectrogram Transformer for AudioSet classification).
---
 .../cpu/audio-classification_fp16_config.json | 60 +++++++++++++++++++
 .../cpu/audio-classification_fp32_config.json | 41 +++++++++++++
 2 files changed, 101 insertions(+)
 create mode 100644 examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp16_config.json
 create mode 100644 examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp32_config.json

diff --git a/examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp16_config.json b/examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp16_config.json
new file mode 100644
index 000000000..6ac10fb42
--- /dev/null
+++ b/examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp16_config.json
@@ -0,0 +1,60 @@
+{
+  "export": {
+    "opset_version": 17,
+    "batch_size": 1,
+    "export_params": true,
+    "do_constant_folding": true,
+    "verbose": false,
+    "dynamo": false,
+    "enable_hierarchy_tags": true,
+    "clean_onnx": false,
+    "hierarchy_tag_format": "full",
+    "input_tensors": [
+      {
+        "name": "input_values",
+        "dtype": "float32",
+        "shape": [
+          1,
+          1024,
+          128
+        ],
+        "value_range": [
+          -1,
+          1
+        ]
+      }
+    ],
+    "output_tensors": [
+      {
+        "name": "logits"
+      }
+    ]
+  },
+  "optim": {},
+  "quant": {
+    "mode": "fp16",
+    "samples": 10,
+    "calibration_method": "minmax",
+    "weight_type": "uint8",
+    "activation_type": "uint8",
+    "per_channel": false,
+    "symmetric": false,
+    "weight_symmetric": null,
+    "activation_symmetric": null,
+    "save_calibration": false,
+    "distribution": "uniform",
+    "seed": null,
+    "calibration_load_path": null,
+    "calibration_save_path": null,
+    "op_types_to_quantize": null,
+    "nodes_to_exclude": null,
+    "fp16_keep_io_types": true,
+    "fp16_op_block_list": null
+  },
+  "compile": null,
+  "loader": {
+    "task": "audio-classification",
+    "model_class": "AutoModelForAudioClassification",
+    "model_type": "audio-spectrogram-transformer"
+  }
+}
diff --git a/examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp32_config.json b/examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp32_config.json
new file mode 100644
index 000000000..439f9edee
--- /dev/null
+++ b/examples/recipes/MIT_ast-finetuned-audioset-10-10-0.4593/cpu/cpu/audio-classification_fp32_config.json
@@ -0,0 +1,41 @@
+{
+  "export": {
+    "opset_version": 17,
+    "batch_size": 1,
+    "export_params": true,
+    "do_constant_folding": true,
+    "verbose": false,
+    "dynamo": false,
+    "enable_hierarchy_tags": true,
+    "clean_onnx": false,
+    "hierarchy_tag_format": "full",
+    "input_tensors": [
+      {
+        "name": "input_values",
+        "dtype": "float32",
+        "shape": [
+          1,
+          1024,
+          128
+        ],
+        "value_range": [
+          -1,
+          1
+        ]
+      }
+    ],
+    "output_tensors": [
+      {
+        "name": "logits"
+      }
+    ]
+  },
+  "optim": {},
+  "quant": null,
+  "compile": null,
+  "loader": {
+    "task": "audio-classification",
+    "model_class": "AutoModelForAudioClassification",
+    "model_type": "audio-spectrogram-transformer"
+  }
+}