add small int8 model

small.en/small.en_cpu_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdd8b5e343bf07e46c8a37e169d6f1f1691e5118ce5c7505f95a1c508646108
+size 442984159

small.en/whisper_cpu_int8_cpu-cpu_metrics .json

@@ -0,0 +1,7 @@
+{
+    "latency-avg": {
+        "value": 9164.66956,
+        "priority": 1,
+        "higher_is_better": false
+    }
+}

small.en/whisper_cpu_int8_cpu-cpu_model.json

@@ -0,0 +1,31 @@
+{
+    "type": "ONNXModel",
+    "config": {
+        "model_path": "/content/Olive/examples/whisper/models/conversion-transformers_optimization-onnx_dynamic_quantization-insert_beam_search-prepost/whisper_cpu_int8_cpu-cpu_model.onnx",
+        "onnx_file_name": null,
+        "inference_settings": null,
+        "use_ort_extensions": true,
+        "hf_config": {
+            "model_name": "openai/whisper-small.en",
+            "task": null,
+            "feature": null,
+            "model_class": "WhisperForConditionalGeneration",
+            "components": [
+                {
+                    "name": "encoder_decoder_init",
+                    "io_config": "get_encdec_io_config",
+                    "component_func": "get_encoder_decoder_init",
+                    "dummy_inputs_func": "encoder_decoder_init_dummy_inputs"
+                },
+                {
+                    "name": "decoder",
+                    "io_config": "get_dec_io_config",
+                    "component_func": "get_decoder",
+                    "dummy_inputs_func": "decoder_dummy_inputs"
+                }
+            ],
+            "dataset": null,
+            "model_loading_args": null
+        }
+    }
+}

small/small-whisper_cpu_int8-2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce1b414bd1a2226d5eda170027c2b77175d0e9d52775b4a3575bafdbb1d3c661
+size 443023501

small/whisper_cpu_int8_cpu-cpu_metrics.json

@@ -0,0 +1,7 @@
+{
+    "latency-avg": {
+        "value": 9404.15679,
+        "priority": 1,
+        "higher_is_better": false
+    }
+}

small/whisper_cpu_int8_cpu-cpu_model.json

@@ -0,0 +1,31 @@
+{
+    "type": "ONNXModel",
+    "config": {
+        "model_path": "/content/Olive/examples/whisper/models/conversion-transformers_optimization-onnx_dynamic_quantization-insert_beam_search-prepost/whisper_cpu_int8_cpu-cpu_model.onnx",
+        "onnx_file_name": null,
+        "inference_settings": null,
+        "use_ort_extensions": true,
+        "hf_config": {
+            "model_name": "openai/whisper-small",
+            "task": null,
+            "feature": null,
+            "model_class": "WhisperForConditionalGeneration",
+            "components": [
+                {
+                    "name": "encoder_decoder_init",
+                    "io_config": "get_encdec_io_config",
+                    "component_func": "get_encoder_decoder_init",
+                    "dummy_inputs_func": "encoder_decoder_init_dummy_inputs"
+                },
+                {
+                    "name": "decoder",
+                    "io_config": "get_dec_io_config",
+                    "component_func": "get_decoder",
+                    "dummy_inputs_func": "decoder_dummy_inputs"
+                }
+            ],
+            "dataset": null,
+            "model_loading_args": null
+        }
+    }
+}