v0.64.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.
- README.md +76 -88
- release_assets.json +5 -5
README.md
CHANGED
|
@@ -14,7 +14,7 @@ pipeline_tag: automatic-speech-recognition
|
|
| 14 |
Distil-Whisper Small English is a distilled version of Whisper Small, optimized for fast and efficient automatic speech recognition.
|
| 15 |
|
| 16 |
This is based on the implementation of Distil-Whisper found [here](https://github.com/huggingface/distil-whisper).
|
| 17 |
-
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 18 |
|
| 19 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 20 |
|
|
@@ -27,23 +27,23 @@ Below are pre-exported model assets ready for deployment.
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
-
| ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.
|
| 31 |
-
| QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.
|
| 32 |
-
| TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[Distil-Whisper on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/distil_whisper)**.
|
| 35 |
|
| 36 |
|
| 37 |
### Option 2: Export with Custom Configurations
|
| 38 |
|
| 39 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 40 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 41 |
- Custom input shapes
|
| 42 |
- Target device and runtime configurations
|
| 43 |
|
| 44 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 45 |
|
| 46 |
-
See our repository for [Distil-Whisper on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
@@ -61,92 +61,80 @@ See our repository for [Distil-Whisper on GitHub](https://github.com/qualcomm/ai
|
|
| 61 |
## Performance Summary
|
| 62 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 63 |
|---|---|---|---|---|---|---
|
| 64 |
-
| decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.
|
| 65 |
-
| decoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.
|
| 66 |
-
| decoder | ONNX | float | Snapdragon® X2 Elite | 5.
|
| 67 |
-
| decoder | ONNX | float | Snapdragon® X Elite | 11.
|
| 68 |
-
| decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.
|
| 69 |
-
| decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile |
|
| 70 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 |
|
| 71 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.
|
| 72 |
-
| decoder | ONNX | float | Qualcomm® QCS8450 |
|
| 73 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 12.
|
| 74 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.
|
| 75 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 7.
|
| 76 |
-
| decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.
|
| 77 |
-
| decoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.
|
| 78 |
-
| decoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.
|
| 79 |
-
| decoder | QNN_DLC | float | Snapdragon® X Elite | 11.
|
| 80 |
-
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.
|
| 81 |
-
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.
|
| 82 |
-
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.
|
| 83 |
-
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.
|
| 84 |
-
| decoder | QNN_DLC | float | Qualcomm®
|
| 85 |
-
| decoder | QNN_DLC | float | Qualcomm®
|
| 86 |
-
| decoder | QNN_DLC | float | Qualcomm®
|
| 87 |
-
| decoder | QNN_DLC | float | Qualcomm®
|
| 88 |
-
| decoder | QNN_DLC | float | Qualcomm®
|
| 89 |
-
| decoder |
|
| 90 |
-
| decoder |
|
| 91 |
-
| decoder |
|
| 92 |
-
| decoder |
|
| 93 |
-
| decoder | TFLITE | float |
|
| 94 |
-
| decoder | TFLITE | float |
|
| 95 |
-
| decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.605 ms | 5 - 554 MB | NPU
|
| 96 |
-
| decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 13.966 ms | 5 - 454 MB | NPU
|
| 97 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.92 ms | 0 - 266 MB | NPU
|
| 98 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.643 ms | 5 - 8 MB | NPU
|
| 99 |
-
| decoder | TFLITE | float | Qualcomm® SA8775P | 13.055 ms | 5 - 358 MB | NPU
|
| 100 |
| decoder | TFLITE | float | Qualcomm® SA8650P | 13.055 ms | 5 - 358 MB | NPU
|
| 101 |
| decoder | TFLITE | float | Qualcomm® SA8255P | 13.055 ms | 5 - 358 MB | NPU
|
| 102 |
-
| decoder | TFLITE | float | Qualcomm® QCS8450 |
|
| 103 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.
|
| 104 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.
|
| 105 |
-
| decoder | TFLITE | float | Qualcomm®
|
| 106 |
-
|
|
| 107 |
-
| encoder | ONNX | float | Snapdragon® 8 Elite
|
| 108 |
-
| encoder | ONNX | float | Snapdragon®
|
| 109 |
-
| encoder | ONNX | float | Snapdragon®
|
| 110 |
-
| encoder | ONNX | float | Snapdragon®
|
| 111 |
-
| encoder | ONNX | float | Snapdragon® 8 Gen
|
| 112 |
-
| encoder | ONNX | float |
|
| 113 |
-
| encoder | ONNX | float | Qualcomm® Dragonwing™
|
| 114 |
-
| encoder | ONNX | float | Qualcomm®
|
| 115 |
-
| encoder | ONNX | float | Qualcomm®
|
| 116 |
-
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-
|
| 117 |
-
| encoder | ONNX | float | Qualcomm® Dragonwing™
|
| 118 |
-
| encoder |
|
| 119 |
-
| encoder | QNN_DLC | float | Snapdragon® 8 Elite
|
| 120 |
-
| encoder | QNN_DLC | float | Snapdragon®
|
| 121 |
-
| encoder | QNN_DLC | float | Snapdragon®
|
| 122 |
-
| encoder | QNN_DLC | float | Snapdragon®
|
| 123 |
-
| encoder | QNN_DLC | float | Snapdragon® 8 Gen
|
| 124 |
-
| encoder | QNN_DLC | float |
|
| 125 |
-
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™
|
| 126 |
-
| encoder | QNN_DLC | float | Qualcomm®
|
| 127 |
-
| encoder | QNN_DLC | float | Qualcomm®
|
| 128 |
-
| encoder | QNN_DLC | float | Qualcomm®
|
| 129 |
-
| encoder | QNN_DLC | float | Qualcomm®
|
| 130 |
-
| encoder | QNN_DLC | float | Qualcomm®
|
| 131 |
-
| encoder |
|
| 132 |
-
| encoder |
|
| 133 |
-
| encoder |
|
| 134 |
-
| encoder |
|
| 135 |
-
| encoder |
|
| 136 |
-
| encoder | TFLITE | float |
|
| 137 |
-
| encoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 414.533 ms | 40 - 78 MB | GPU
|
| 138 |
-
| encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 477.419 ms | 39 - 182 MB | GPU
|
| 139 |
-
| encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 846.172 ms | 40 - 194 MB | GPU
|
| 140 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2994.928 ms | 0 - 39 MB | GPU
|
| 141 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 652.165 ms | 0 - 318 MB | GPU
|
| 142 |
-
| encoder | TFLITE | float | Qualcomm® SA8775P | 1325.637 ms | 38 - 83 MB | GPU
|
| 143 |
| encoder | TFLITE | float | Qualcomm® SA8650P | 1325.637 ms | 38 - 83 MB | GPU
|
| 144 |
| encoder | TFLITE | float | Qualcomm® SA8255P | 1325.637 ms | 38 - 83 MB | GPU
|
| 145 |
-
| encoder | TFLITE | float | Qualcomm® QCS8450 |
|
| 146 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 147 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 |
|
| 148 |
-
| encoder | TFLITE | float | Qualcomm®
|
| 149 |
-
| encoder | TFLITE | float | Qualcomm® SA8295P | 685.442 ms | 38 - 82 MB | GPU
|
| 150 |
|
| 151 |
## License
|
| 152 |
* The license for the original implementation of Distil-Whisper can be found
|
|
|
|
| 14 |
Distil-Whisper Small English is a distilled version of Whisper Small, optimized for fast and efficient automatic speech recognition.
|
| 15 |
|
| 16 |
This is based on the implementation of Distil-Whisper found [here](https://github.com/huggingface/distil-whisper).
|
| 17 |
+
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/distil_whisper) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
|
| 18 |
|
| 19 |
Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
|
| 20 |
|
|
|
|
| 27 |
|
| 28 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 29 |
|---|---|---|---|---|
|
| 30 |
+
| ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.64.0/distil_whisper-onnx-float.zip)
|
| 31 |
+
| QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.64.0/distil_whisper-qnn_dlc-float.zip)
|
| 32 |
+
| TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.64.0/distil_whisper-tflite-float.zip)
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[Distil-Whisper on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/distil_whisper)**.
|
| 35 |
|
| 36 |
|
| 37 |
### Option 2: Export with Custom Configurations
|
| 38 |
|
| 39 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/distil_whisper) Python library to compile and export the model with your own:
|
| 40 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 41 |
- Custom input shapes
|
| 42 |
- Target device and runtime configurations
|
| 43 |
|
| 44 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 45 |
|
| 46 |
+
See our repository for [Distil-Whisper on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/distil_whisper) for usage instructions.
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
|
|
| 61 |
## Performance Summary
|
| 62 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 63 |
|---|---|---|---|---|---|---
|
| 64 |
+
| decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.589 ms | 10 - 354 MB | NPU
|
| 65 |
+
| decoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.321 ms | 15 - 369 MB | NPU
|
| 66 |
+
| decoder | ONNX | float | Snapdragon® X2 Elite | 5.066 ms | 40 - 40 MB | NPU
|
| 67 |
+
| decoder | ONNX | float | Snapdragon® X Elite | 11.242 ms | 179 - 179 MB | NPU
|
| 68 |
+
| decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.847 ms | 23 - 497 MB | NPU
|
| 69 |
+
| decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.093 ms | 50 - 389 MB | NPU
|
| 70 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 12.997 ms | 40 - 84 MB | NPU
|
| 71 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.697 ms | 0 - 181 MB | NPU
|
| 72 |
+
| decoder | ONNX | float | Qualcomm® QCS8450 | 14.093 ms | 50 - 389 MB | NPU
|
| 73 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 12.811 ms | 40 - 83 MB | NPU
|
| 74 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.242 ms | 179 - 179 MB | NPU
|
| 75 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 7.321 ms | 15 - 369 MB | NPU
|
| 76 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.75 ms | 1 - 331 MB | NPU
|
| 77 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.371 ms | 5 - 348 MB | NPU
|
| 78 |
+
| decoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.541 ms | 40 - 40 MB | NPU
|
| 79 |
+
| decoder | QNN_DLC | float | Snapdragon® X Elite | 11.494 ms | 40 - 40 MB | NPU
|
| 80 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.768 ms | 0 - 428 MB | NPU
|
| 81 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.627 ms | 32 - 322 MB | NPU
|
| 82 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.886 ms | 40 - 87 MB | NPU
|
| 83 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.496 ms | 40 - 42 MB | NPU
|
| 84 |
+
| decoder | QNN_DLC | float | Qualcomm® QCS8450 | 13.627 ms | 32 - 322 MB | NPU
|
| 85 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 12.615 ms | 40 - 87 MB | NPU
|
| 86 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.494 ms | 40 - 40 MB | NPU
|
| 87 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.371 ms | 5 - 348 MB | NPU
|
| 88 |
+
| decoder | QNN_DLC | float | Qualcomm® SA8295P | 14.013 ms | 5 - 201 MB | NPU
|
| 89 |
+
| decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.866 ms | 5 - 385 MB | NPU
|
| 90 |
+
| decoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.178 ms | 4 - 370 MB | NPU
|
| 91 |
+
| decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.717 ms | 3 - 550 MB | NPU
|
| 92 |
+
| decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.129 ms | 5 - 453 MB | NPU
|
| 93 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.735 ms | 0 - 266 MB | NPU
|
| 94 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.721 ms | 5 - 8 MB | NPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
| decoder | TFLITE | float | Qualcomm® SA8650P | 13.055 ms | 5 - 358 MB | NPU
|
| 96 |
| decoder | TFLITE | float | Qualcomm® SA8255P | 13.055 ms | 5 - 358 MB | NPU
|
| 97 |
+
| decoder | TFLITE | float | Qualcomm® QCS8450 | 14.129 ms | 5 - 453 MB | NPU
|
| 98 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.88 ms | 0 - 265 MB | NPU
|
| 99 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.178 ms | 4 - 370 MB | NPU
|
| 100 |
+
| decoder | TFLITE | float | Qualcomm® SA8295P | 13.93 ms | 5 - 260 MB | NPU
|
| 101 |
+
| encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 53.931 ms | 80 - 648 MB | NPU
|
| 102 |
+
| encoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 65.65 ms | 62 - 608 MB | NPU
|
| 103 |
+
| encoder | ONNX | float | Snapdragon® X2 Elite | 55.186 ms | 133 - 133 MB | NPU
|
| 104 |
+
| encoder | ONNX | float | Snapdragon® X Elite | 118.938 ms | 236 - 236 MB | NPU
|
| 105 |
+
| encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 90.041 ms | 40 - 965 MB | NPU
|
| 106 |
+
| encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 177.436 ms | 76 - 965 MB | NPU
|
| 107 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 148.425 ms | 74 - 79 MB | NPU
|
| 108 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 117.785 ms | 0 - 258 MB | NPU
|
| 109 |
+
| encoder | ONNX | float | Qualcomm® QCS8450 | 177.436 ms | 76 - 965 MB | NPU
|
| 110 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 140.743 ms | 80 - 84 MB | NPU
|
| 111 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 118.938 ms | 236 - 236 MB | NPU
|
| 112 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 65.65 ms | 62 - 608 MB | NPU
|
| 113 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 53.71 ms | 0 - 547 MB | NPU
|
| 114 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 65.465 ms | 0 - 526 MB | NPU
|
| 115 |
+
| encoder | QNN_DLC | float | Snapdragon® X2 Elite | 55.499 ms | 1 - 1 MB | NPU
|
| 116 |
+
| encoder | QNN_DLC | float | Snapdragon® X Elite | 118.403 ms | 1 - 1 MB | NPU
|
| 117 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 87.105 ms | 0 - 800 MB | NPU
|
| 118 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 176.442 ms | 0 - 765 MB | NPU
|
| 119 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 145.694 ms | 1 - 40 MB | NPU
|
| 120 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 116.256 ms | 4 - 10 MB | NPU
|
| 121 |
+
| encoder | QNN_DLC | float | Qualcomm® QCS8450 | 176.442 ms | 0 - 765 MB | NPU
|
| 122 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 140.671 ms | 1 - 39 MB | NPU
|
| 123 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 118.403 ms | 1 - 1 MB | NPU
|
| 124 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 65.465 ms | 0 - 526 MB | NPU
|
| 125 |
+
| encoder | QNN_DLC | float | Qualcomm® SA8295P | 174.649 ms | 1 - 501 MB | NPU
|
| 126 |
+
| encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 368.621 ms | 42 - 83 MB | GPU
|
| 127 |
+
| encoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 416.444 ms | 17 - 55 MB | GPU
|
| 128 |
+
| encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 477.188 ms | 14 - 157 MB | GPU
|
| 129 |
+
| encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 841.465 ms | 40 - 194 MB | GPU
|
| 130 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2985.565 ms | 0 - 39 MB | GPU
|
| 131 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 655.81 ms | 0 - 311 MB | GPU
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
| encoder | TFLITE | float | Qualcomm® SA8650P | 1325.637 ms | 38 - 83 MB | GPU
|
| 133 |
| encoder | TFLITE | float | Qualcomm® SA8255P | 1325.637 ms | 38 - 83 MB | GPU
|
| 134 |
+
| encoder | TFLITE | float | Qualcomm® QCS8450 | 841.465 ms | 40 - 194 MB | GPU
|
| 135 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1322.379 ms | 0 - 39 MB | GPU
|
| 136 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 416.444 ms | 17 - 55 MB | GPU
|
| 137 |
+
| encoder | TFLITE | float | Qualcomm® SA8295P | 689.302 ms | 38 - 82 MB | GPU
|
|
|
|
| 138 |
|
| 139 |
## License
|
| 140 |
* The license for the original implementation of Distil-Whisper can be found
|
release_assets.json
CHANGED
|
@@ -1,24 +1,24 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
"qairt": "2.50.0.260828221209",
|
| 9 |
-
"onnx_runtime": "1.
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
"qairt": "2.50.0.260828221209"
|
| 16 |
},
|
| 17 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.
|
| 18 |
},
|
| 19 |
"tflite": {
|
| 20 |
"tool_versions": {},
|
| 21 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.
|
| 22 |
}
|
| 23 |
}
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.64.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
"qairt": "2.50.0.260828221209",
|
| 9 |
+
"onnx_runtime": "1.30.0"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.64.0/distil_whisper-onnx-float.zip"
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
"qairt": "2.50.0.260828221209"
|
| 16 |
},
|
| 17 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.64.0/distil_whisper-qnn_dlc-float.zip"
|
| 18 |
},
|
| 19 |
"tflite": {
|
| 20 |
"tool_versions": {},
|
| 21 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.64.0/distil_whisper-tflite-float.zip"
|
| 22 |
}
|
| 23 |
}
|
| 24 |
}
|