v0.34.0

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

README.md

@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/huggingface_wavlm_base_plus).
 
 
+
 ### Model Details
 
 - **Model Type:** Model_use_case.speech_recognition
@@ -35,31 +36,31 @@ More details on model performance across various devices, can be found
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 813.913 ms | 0 - 806 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 814.068 ms | 0 - 805 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 872.273 ms | 1 - 827 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 552.123 ms | 0 - 1192 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 549.073 ms | 0 - 1192 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 578.052 ms | 0 - 925 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 259.639 ms | 0 - 55 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 257.914 ms | 0 - 53 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 290.655 ms | 3 - 54 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 306.442 ms | 0 - 805 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 306.675 ms | 0 - 804 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 324.338 ms | 1 - 826 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 813.913 ms | 0 - 806 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 814.068 ms | 0 - 805 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 872.273 ms | 1 - 827 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 259.884 ms | 0 - 57 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 258.884 ms | 0 - 53 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 292.19 ms | 0 - 51 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 580.268 ms | 0 - 1100 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 580.917 ms | 0 - 1100 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 448.219 ms | 1 - 976 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 262.478 ms | 0 - 56 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 260.218 ms | 0 - 52 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 291.549 ms | 0 - 50 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 306.442 ms | 0 - 805 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 306.675 ms | 0 - 804 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 324.338 ms | 1 - 826 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
-| HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 260.269 ms | 0 - 54 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 261.021 ms | 0 - 56 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 293.176 ms | 0 - 50 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
 | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 475.477 ms | 1 - 51 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
-| HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 181.862 ms | 0 - 856 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 182.929 ms | 0 - 848 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 216.247 ms | 1 - 1015 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
 | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 348.261 ms | 1 - 961 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
-| HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 171.769 ms | 0 - 800 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
+| HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 170.569 ms | 0 - 800 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 221.424 ms | 0 - 703 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
 | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 278.897 ms | 1 - 813 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
 | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 313.971 ms | 285 - 285 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
@@ -121,17 +122,7 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.huggingface_wavlm_base_plus.export
 ```
-```
-Profiling Results
-------------------------------------------------------------
-HuggingFace-WavLM-Base-Plus
-Device                          : cs_8275 (ANDROID 14)                 
-Runtime                         : TFLITE                               
-Estimated inference time (ms)   : 813.9                                
-Estimated peak memory usage (MB): [0, 806]                             
-Total # Ops                     : 873                                  
-Compute Unit(s)                 : npu (873 ops) gpu (0 ops) cpu (0 ops)
-```
+
 
 
 ## How does this work?

precompiled/qualcomm-snapdragon-x-elite/HuggingFace-WavLM-Base-Plus.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087d6ce3f5a49a4bdad273f4d6ec6b987848802c2bb9a23cf2a6d4c59ee1c47f
+oid sha256:76bbd3dbc8fadf7ac999adee98db689e350acd0b51597dfca379f5b2db9d0079
 size 213848952

precompiled/qualcomm-snapdragon-x-elite/HuggingFace-WavLM-Base-Plus.onnx.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a163065d9ab5a3d372d49f85a4126c367313457874bae16ae38698e093422635
-size 180613788
+oid sha256:66d9b691eb12fc6356dac23934c11fd750bd5a239cff8de756a39f9d01572b1d
+size 180614190

precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml

@@ -0,0 +1,5 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.34.2.250528164111_119506
+  precompiled_qnn_onnx:
+    qairt: 2.33.2.250410134701_117956