v0.50.2
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.50.2 for changelog.
- README.md +62 -62
- release_assets.json +1 -1
README.md
CHANGED
|
@@ -28,26 +28,26 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 32 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 33 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 34 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 35 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 36 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 37 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 38 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 39 |
-
| PRECOMPILED_QNN_ONNX | w8a16 |
|
| 40 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 41 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 42 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 43 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 44 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 45 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 46 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 47 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 48 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 49 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 50 |
-
| QNN_CONTEXT_BINARY | w8a16 |
|
| 51 |
|
| 52 |
For more device-specific assets and performance metrics, visit **[Whisper-Small-Quantized on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small_quantized)**.
|
| 53 |
|
|
@@ -75,48 +75,48 @@ See our repository for [Whisper-Small-Quantized on GitHub](https://github.com/qu
|
|
| 75 |
## Performance Summary
|
| 76 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 77 |
|---|---|---|---|---|---|---
|
| 78 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 79 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.
|
| 80 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 7.
|
| 81 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.
|
| 82 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.
|
| 83 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 9.
|
| 84 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 |
|
| 85 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.
|
| 86 |
-
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.
|
| 87 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.
|
| 88 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.
|
| 89 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.
|
| 90 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.
|
| 91 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 13.
|
| 92 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.
|
| 93 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P |
|
| 94 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 8.
|
| 95 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 |
|
| 96 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 13.
|
| 97 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.
|
| 98 |
-
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.
|
| 99 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 100 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite |
|
| 101 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite |
|
| 102 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile |
|
| 103 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) |
|
| 104 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 255.
|
| 105 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 |
|
| 106 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 200.
|
| 107 |
-
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 457.
|
| 108 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile |
|
| 109 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite |
|
| 110 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite |
|
| 111 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile |
|
| 112 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) |
|
| 113 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) |
|
| 114 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P |
|
| 115 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 |
|
| 116 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 |
|
| 117 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P |
|
| 118 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile |
|
| 119 |
-
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile |
|
| 120 |
|
| 121 |
## License
|
| 122 |
* The license for the original implementation of Whisper-Small-Quantized can be found
|
|
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_qcm6690 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip)
|
| 32 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_qcs8550_proxy | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip)
|
| 33 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_qcs9075 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip)
|
| 34 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_7gen4 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip)
|
| 35 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_8_elite_for_galaxy | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 36 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_8_elite_gen5 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
|
| 37 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_8gen3 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip)
|
| 38 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_x2_elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip)
|
| 39 |
+
| PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_x_elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip)
|
| 40 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_qcm6690 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip)
|
| 41 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_qcs8550_proxy | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip)
|
| 42 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_qcs9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.zip)
|
| 43 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_sa7255p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip)
|
| 44 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_sa8775p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip)
|
| 45 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_7gen4 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip)
|
| 46 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_8_elite_for_galaxy | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 47 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_8_elite_gen5 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
|
| 48 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_8gen3 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip)
|
| 49 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_x2_elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip)
|
| 50 |
+
| QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_x_elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip)
|
| 51 |
|
| 52 |
For more device-specific assets and performance metrics, visit **[Whisper-Small-Quantized on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small_quantized)**.
|
| 53 |
|
|
|
|
| 75 |
## Performance Summary
|
| 76 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 77 |
|---|---|---|---|---|---|---
|
| 78 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.979 ms | 38 - 48 MB | NPU
|
| 79 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.812 ms | 185 - 185 MB | NPU
|
| 80 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 7.967 ms | 185 - 185 MB | NPU
|
| 81 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.354 ms | 40 - 48 MB | NPU
|
| 82 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.319 ms | 29 - 32 MB | NPU
|
| 83 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 9.06 ms | 24 - 57 MB | NPU
|
| 84 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 37.459 ms | 29 - 39 MB | NPU
|
| 85 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.757 ms | 25 - 33 MB | NPU
|
| 86 |
+
| decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.823 ms | 30 - 36 MB | NPU
|
| 87 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.963 ms | 30 - 40 MB | NPU
|
| 88 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.191 ms | 30 - 30 MB | NPU
|
| 89 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.57 ms | 30 - 30 MB | NPU
|
| 90 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.254 ms | 30 - 39 MB | NPU
|
| 91 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 13.457 ms | 13 - 20 MB | NPU
|
| 92 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.158 ms | 30 - 32 MB | NPU
|
| 93 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 9.257 ms | 29 - 38 MB | NPU
|
| 94 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 8.92 ms | 25 - 60 MB | NPU
|
| 95 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 36.842 ms | 30 - 37 MB | NPU
|
| 96 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 13.457 ms | 13 - 20 MB | NPU
|
| 97 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.751 ms | 22 - 35 MB | NPU
|
| 98 |
+
| decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.848 ms | 30 - 37 MB | NPU
|
| 99 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 175.256 ms | 63 - 73 MB | NPU
|
| 100 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 154.028 ms | 127 - 127 MB | NPU
|
| 101 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 264.69 ms | 127 - 127 MB | NPU
|
| 102 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 244.062 ms | 63 - 75 MB | NPU
|
| 103 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 350.116 ms | 55 - 58 MB | NPU
|
| 104 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 255.908 ms | 63 - 66 MB | NPU
|
| 105 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 4170.586 ms | 2 - 13 MB | NPU
|
| 106 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 200.797 ms | 63 - 75 MB | NPU
|
| 107 |
+
| encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 457.805 ms | 56 - 66 MB | NPU
|
| 108 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 175.95 ms | 1 - 11 MB | NPU
|
| 109 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 153.643 ms | 0 - 0 MB | NPU
|
| 110 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 296.075 ms | 0 - 0 MB | NPU
|
| 111 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 269.335 ms | 1 - 8 MB | NPU
|
| 112 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 518.268 ms | 1 - 9 MB | NPU
|
| 113 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 368.292 ms | 1 - 2 MB | NPU
|
| 114 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 312.155 ms | 1 - 10 MB | NPU
|
| 115 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 293.695 ms | 0 - 29 MB | NPU
|
| 116 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 4234.28 ms | 0 - 7 MB | NPU
|
| 117 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 518.268 ms | 1 - 9 MB | NPU
|
| 118 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 221.77 ms | 1 - 14 MB | NPU
|
| 119 |
+
| encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 468.035 ms | 1 - 7 MB | NPU
|
| 120 |
|
| 121 |
## License
|
| 122 |
* The license for the original implementation of Whisper-Small-Quantized can be found
|
release_assets.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"version":"0.50.
|
|
|
|
| 1 |
+
{"version":"0.50.2","precisions":{"w8a16":{"chipset_assets":{"qualcomm_qcm6690":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip"}},"qualcomm_qcs8550_proxy":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip"}},"qualcomm_qcs9075":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip"}},"qualcomm_sa7255p":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip"}},"qualcomm_sa8775p":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip"}},"qualcomm_snapdragon_7gen4":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip"}},"qualcomm_snapdragon_8_elite_for_galaxy":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip"}},"qualcomm_snapdragon_8_elite_gen5":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip"}},"qualcomm_snapdragon_8gen3":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip"}},"qualcomm_snapdragon_x2_elite":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip"}},"qualcomm_snapdragon_x_elite":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip"}}}}}}
|