v0.49.1
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.
README.md
CHANGED
|
@@ -28,24 +28,24 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 32 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 33 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 34 |
-
| PRECOMPILED_QNN_ONNX | float |
|
| 35 |
-
| PRECOMPILED_QNN_ONNX | float |
|
| 36 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite
|
| 37 |
-
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.
|
| 38 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 39 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 40 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 41 |
-
| QNN_CONTEXT_BINARY | float |
|
| 42 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 43 |
-
| QNN_CONTEXT_BINARY | float |
|
| 44 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite
|
| 45 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.
|
| 46 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.
|
| 47 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.
|
| 48 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.
|
| 49 |
|
| 50 |
For more device-specific assets and performance metrics, visit **[Whisper-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_base)**.
|
| 51 |
|
|
@@ -77,44 +77,44 @@ See our repository for [Whisper-Base on GitHub](https://github.com/qualcomm/ai-h
|
|
| 77 |
## Performance Summary
|
| 78 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 79 |
|---|---|---|---|---|---|---
|
| 80 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 81 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 82 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 83 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float |
|
| 84 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Qualcomm®
|
| 85 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float |
|
| 86 |
-
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite
|
| 87 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 88 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 89 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 90 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float |
|
| 91 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 92 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 93 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 94 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 95 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 96 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 97 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float |
|
| 98 |
-
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite
|
| 99 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 100 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 101 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon®
|
| 102 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float |
|
| 103 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Qualcomm®
|
| 104 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float |
|
| 105 |
-
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite
|
| 106 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 107 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 108 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon®
|
| 109 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float |
|
| 110 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 111 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 112 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 113 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 114 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 115 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm®
|
| 116 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float |
|
| 117 |
-
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite
|
| 118 |
|
| 119 |
## License
|
| 120 |
* The license for the original implementation of Whisper-Base can be found
|
|
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip)
|
| 32 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
|
| 33 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
|
| 34 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
|
| 35 |
+
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
|
| 36 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 37 |
+
| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
|
| 38 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip)
|
| 39 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
|
| 40 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
|
| 41 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
|
| 42 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
|
| 43 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_sa8775p.zip)
|
| 44 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 45 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_sa7255p.zip)
|
| 46 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_sa8295p.zip)
|
| 47 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_qcs9075.zip)
|
| 48 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.49.1/whisper_base-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip)
|
| 49 |
|
| 50 |
For more device-specific assets and performance metrics, visit **[Whisper-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_base)**.
|
| 51 |
|
|
|
|
| 77 |
## Performance Summary
|
| 78 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 79 |
|---|---|---|---|---|---|---
|
| 80 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.476 ms | 20 - 30 MB | NPU
|
| 81 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 1.896 ms | 126 - 126 MB | NPU
|
| 82 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 3.296 ms | 125 - 125 MB | NPU
|
| 83 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.21 ms | 0 - 8 MB | NPU
|
| 84 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.013 ms | 20 - 22 MB | NPU
|
| 85 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 4.629 ms | 20 - 43 MB | NPU
|
| 86 |
+
| HfWhisperDecoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.692 ms | 3 - 10 MB | NPU
|
| 87 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.473 ms | 20 - 30 MB | NPU
|
| 88 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 2.416 ms | 20 - 20 MB | NPU
|
| 89 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 3.327 ms | 20 - 20 MB | NPU
|
| 90 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 3.195 ms | 20 - 27 MB | NPU
|
| 91 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 6.533 ms | 20 - 28 MB | NPU
|
| 92 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 3.873 ms | 17 - 19 MB | NPU
|
| 93 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 4.864 ms | 20 - 29 MB | NPU
|
| 94 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 4.663 ms | 20 - 44 MB | NPU
|
| 95 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 5.161 ms | 20 - 28 MB | NPU
|
| 96 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 6.533 ms | 20 - 28 MB | NPU
|
| 97 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 5.414 ms | 18 - 23 MB | NPU
|
| 98 |
+
| HfWhisperDecoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.648 ms | 0 - 9 MB | NPU
|
| 99 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 14.926 ms | 38 - 48 MB | NPU
|
| 100 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 15.4 ms | 64 - 64 MB | NPU
|
| 101 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 37.311 ms | 67 - 67 MB | NPU
|
| 102 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 27.052 ms | 41 - 48 MB | NPU
|
| 103 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 36.746 ms | 3 - 52 MB | NPU
|
| 104 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 44.398 ms | 40 - 44 MB | NPU
|
| 105 |
+
| HfWhisperEncoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.182 ms | 39 - 46 MB | NPU
|
| 106 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 14.536 ms | 0 - 10 MB | NPU
|
| 107 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 15.857 ms | 0 - 0 MB | NPU
|
| 108 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 37.311 ms | 0 - 0 MB | NPU
|
| 109 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 27.405 ms | 1 - 8 MB | NPU
|
| 110 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 120.039 ms | 1 - 10 MB | NPU
|
| 111 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 36.495 ms | 1 - 17 MB | NPU
|
| 112 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 43.755 ms | 1 - 10 MB | NPU
|
| 113 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 45.253 ms | 0 - 20 MB | NPU
|
| 114 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 97.486 ms | 1 - 10 MB | NPU
|
| 115 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 120.039 ms | 1 - 10 MB | NPU
|
| 116 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 74.091 ms | 1 - 6 MB | NPU
|
| 117 |
+
| HfWhisperEncoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.248 ms | 1 - 10 MB | NPU
|
| 118 |
|
| 119 |
## License
|
| 120 |
* The license for the original implementation of Whisper-Base can be found
|