v0.63.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.
- README.md +78 -84
- release_assets.json +7 -7
README.md
CHANGED
|
@@ -14,7 +14,7 @@ pipeline_tag: image-to-text
|
|
| 14 |
End-to-end text recognition approach with pre-trained image transformer and text transformer models for both image understanding and wordpiece-level text generation.
|
| 15 |
|
| 16 |
This is based on the implementation of TrOCR found [here](https://huggingface.co/microsoft/trocr-small-handwritten).
|
| 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.
|
| 31 |
-
| QNN_DLC | float | Universal | QAIRT 2.
|
| 32 |
-
| TFLITE | float | Universal | QAIRT 2.
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[TrOCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/trocr)**.
|
| 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 [TrOCR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
@@ -60,92 +60,86 @@ See our repository for [TrOCR on GitHub](https://github.com/qualcomm/ai-hub-mode
|
|
| 60 |
## Performance Summary
|
| 61 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 62 |
|---|---|---|---|---|---|---
|
| 63 |
-
| decoder | ONNX | float | Snapdragon®
|
| 64 |
-
| decoder | ONNX | float | Snapdragon®
|
| 65 |
-
| decoder | ONNX | float | Snapdragon®
|
| 66 |
-
| decoder | ONNX | float | Snapdragon®
|
| 67 |
-
| decoder | ONNX | float |
|
| 68 |
-
| decoder | ONNX | float |
|
| 69 |
-
| decoder | ONNX | float | Qualcomm®
|
| 70 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™
|
| 71 |
-
| decoder | ONNX | float | Qualcomm®
|
| 72 |
-
| decoder | ONNX | float | Qualcomm® Dragonwing™
|
| 73 |
-
| decoder | ONNX | float |
|
| 74 |
-
| decoder | ONNX | float |
|
| 75 |
-
| decoder | QNN_DLC | float | Snapdragon®
|
| 76 |
-
| decoder | QNN_DLC | float | Snapdragon®
|
| 77 |
-
| decoder | QNN_DLC | float | Snapdragon®
|
| 78 |
-
| decoder | QNN_DLC | float | Snapdragon®
|
| 79 |
-
| decoder | QNN_DLC | float |
|
| 80 |
-
| decoder | QNN_DLC | float |
|
| 81 |
-
| decoder | QNN_DLC | float | Qualcomm®
|
|
|
|
| 82 |
| decoder | QNN_DLC | float | Qualcomm® SA8650P | 2.892 ms | 5 - 106 MB | NPU
|
| 83 |
| decoder | QNN_DLC | float | Qualcomm® SA8255P | 2.892 ms | 5 - 106 MB | NPU
|
| 84 |
-
| decoder | QNN_DLC | float | Qualcomm® QCS8450 | 2.
|
| 85 |
-
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.
|
| 86 |
-
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.
|
| 87 |
-
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.
|
| 88 |
-
| decoder | QNN_DLC | float | Qualcomm® SA7255P | 4.
|
| 89 |
-
| decoder | QNN_DLC | float | Qualcomm® SA8295P | 2.
|
| 90 |
-
| decoder |
|
| 91 |
-
| decoder |
|
| 92 |
-
| decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.
|
| 93 |
-
| decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.
|
| 94 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2.
|
| 95 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.
|
| 96 |
-
| decoder | TFLITE | float | Qualcomm® SA8775P | 2.84 ms | 0 - 104 MB | NPU
|
| 97 |
| decoder | TFLITE | float | Qualcomm® SA8650P | 2.84 ms | 0 - 104 MB | NPU
|
| 98 |
| decoder | TFLITE | float | Qualcomm® SA8255P | 2.84 ms | 0 - 104 MB | NPU
|
| 99 |
-
| decoder | TFLITE | float | Qualcomm® QCS8450 | 2.
|
| 100 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 2.
|
| 101 |
-
| decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.
|
| 102 |
-
| decoder | TFLITE | float | Qualcomm®
|
| 103 |
-
|
|
| 104 |
-
|
|
| 105 |
-
|
|
| 106 |
-
| encoder | ONNX | float | Snapdragon®
|
| 107 |
-
| encoder | ONNX | float | Snapdragon®
|
| 108 |
-
| encoder | ONNX | float | Snapdragon® 8 Gen
|
| 109 |
-
| encoder | ONNX | float |
|
| 110 |
-
| encoder | ONNX | float | Qualcomm® Dragonwing™
|
| 111 |
-
| encoder | ONNX | float | Qualcomm®
|
| 112 |
-
| encoder | ONNX | float | Qualcomm®
|
| 113 |
-
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-
|
| 114 |
-
| encoder | ONNX | float | Qualcomm® Dragonwing™
|
| 115 |
-
| encoder |
|
| 116 |
-
| encoder |
|
| 117 |
-
| encoder |
|
| 118 |
-
| encoder | QNN_DLC | float | Snapdragon®
|
| 119 |
-
| encoder | QNN_DLC | float | Snapdragon®
|
| 120 |
-
| encoder | QNN_DLC | float | Snapdragon® 8 Gen
|
| 121 |
-
| encoder | QNN_DLC | float |
|
| 122 |
-
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™
|
| 123 |
-
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.316 ms | 2 - 3 MB | NPU
|
| 124 |
-
| encoder | QNN_DLC | float | Qualcomm® SA8775P | 14.024 ms | 2 - 108 MB | NPU
|
| 125 |
| encoder | QNN_DLC | float | Qualcomm® SA8650P | 14.024 ms | 2 - 108 MB | NPU
|
| 126 |
| encoder | QNN_DLC | float | Qualcomm® SA8255P | 14.024 ms | 2 - 108 MB | NPU
|
| 127 |
-
| encoder | QNN_DLC | float | Qualcomm® QCS8450 |
|
| 128 |
-
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 13.
|
| 129 |
-
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 |
|
| 130 |
-
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 5.
|
| 131 |
-
| encoder | QNN_DLC | float | Qualcomm® SA7255P |
|
| 132 |
-
| encoder | QNN_DLC | float | Qualcomm® SA8295P |
|
| 133 |
-
| encoder |
|
| 134 |
-
| encoder |
|
| 135 |
-
| encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.
|
| 136 |
-
| encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile |
|
| 137 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.
|
| 138 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.
|
| 139 |
-
| encoder | TFLITE | float | Qualcomm® SA8775P | 13.479 ms | 7 - 111 MB | NPU
|
| 140 |
| encoder | TFLITE | float | Qualcomm® SA8650P | 13.479 ms | 7 - 111 MB | NPU
|
| 141 |
| encoder | TFLITE | float | Qualcomm® SA8255P | 13.479 ms | 7 - 111 MB | NPU
|
| 142 |
-
| encoder | TFLITE | float | Qualcomm® QCS8450 |
|
| 143 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 |
|
| 144 |
-
| encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 5.
|
| 145 |
-
| encoder | TFLITE | float | Qualcomm®
|
| 146 |
-
| encoder | TFLITE | float | Qualcomm® SA8295P | 19.064 ms | 7 - 237 MB | NPU
|
| 147 |
-
| encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 5.186 ms | 6 - 111 MB | NPU
|
| 148 |
-
| encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.093 ms | 0 - 105 MB | NPU
|
| 149 |
|
| 150 |
## License
|
| 151 |
* The license for the original implementation of TrOCR can be found
|
|
|
|
| 14 |
End-to-end text recognition approach with pre-trained image transformer and text transformer models for both image understanding and wordpiece-level text generation.
|
| 15 |
|
| 16 |
This is based on the implementation of TrOCR found [here](https://huggingface.co/microsoft/trocr-small-handwritten).
|
| 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/v0.63.0/src/qai_hub_models/models/trocr) 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.63.0/trocr-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/trocr/releases/v0.63.0/trocr-qnn_dlc-float.zip)
|
| 32 |
+
| TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.63.0/trocr-tflite-float.zip)
|
| 33 |
|
| 34 |
For more device-specific assets and performance metrics, visit **[TrOCR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/trocr)**.
|
| 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/v0.63.0/src/qai_hub_models/models/trocr) 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 [TrOCR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/trocr) for usage instructions.
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
|
|
| 60 |
## Performance Summary
|
| 61 |
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|
| 62 |
|---|---|---|---|---|---|---
|
| 63 |
+
| decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.304 ms | 2 - 184 MB | NPU
|
| 64 |
+
| decoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.282 ms | 0 - 196 MB | NPU
|
| 65 |
+
| decoder | ONNX | float | Snapdragon® X2 Elite | 1.267 ms | 7 - 7 MB | NPU
|
| 66 |
+
| decoder | ONNX | float | Snapdragon® X Elite | 1.931 ms | 68 - 68 MB | NPU
|
| 67 |
+
| decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.512 ms | 0 - 285 MB | NPU
|
| 68 |
+
| decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.313 ms | 1 - 224 MB | NPU
|
| 69 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 2.811 ms | 7 - 18 MB | NPU
|
| 70 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.106 ms | 1 - 4 MB | NPU
|
| 71 |
+
| decoder | ONNX | float | Qualcomm® QCS8450 | 2.313 ms | 1 - 224 MB | NPU
|
| 72 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.759 ms | 7 - 17 MB | NPU
|
| 73 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.931 ms | 68 - 68 MB | NPU
|
| 74 |
+
| decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.282 ms | 0 - 196 MB | NPU
|
| 75 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.278 ms | 2 - 178 MB | NPU
|
| 76 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.257 ms | 0 - 189 MB | NPU
|
| 77 |
+
| decoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.701 ms | 7 - 7 MB | NPU
|
| 78 |
+
| decoder | QNN_DLC | float | Snapdragon® X Elite | 2.156 ms | 7 - 7 MB | NPU
|
| 79 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.449 ms | 0 - 278 MB | NPU
|
| 80 |
+
| decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.277 ms | 2 - 223 MB | NPU
|
| 81 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2.661 ms | 7 - 17 MB | NPU
|
| 82 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.015 ms | 1 - 3 MB | NPU
|
| 83 |
| decoder | QNN_DLC | float | Qualcomm® SA8650P | 2.892 ms | 5 - 106 MB | NPU
|
| 84 |
| decoder | QNN_DLC | float | Qualcomm® SA8255P | 2.892 ms | 5 - 106 MB | NPU
|
| 85 |
+
| decoder | QNN_DLC | float | Qualcomm® QCS8450 | 2.277 ms | 2 - 223 MB | NPU
|
| 86 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.602 ms | 7 - 16 MB | NPU
|
| 87 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.156 ms | 7 - 7 MB | NPU
|
| 88 |
+
| decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.257 ms | 0 - 189 MB | NPU
|
| 89 |
+
| decoder | QNN_DLC | float | Qualcomm® SA7255P | 4.13 ms | 7 - 110 MB | NPU
|
| 90 |
+
| decoder | QNN_DLC | float | Qualcomm® SA8295P | 2.595 ms | 0 - 45 MB | NPU
|
| 91 |
+
| decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 1.257 ms | 0 - 179 MB | NPU
|
| 92 |
+
| decoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.239 ms | 0 - 192 MB | NPU
|
| 93 |
+
| decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.42 ms | 18 - 301 MB | NPU
|
| 94 |
+
| decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.271 ms | 0 - 220 MB | NPU
|
| 95 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2.665 ms | 0 - 84 MB | NPU
|
| 96 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.98 ms | 0 - 3 MB | NPU
|
|
|
|
| 97 |
| decoder | TFLITE | float | Qualcomm® SA8650P | 2.84 ms | 0 - 104 MB | NPU
|
| 98 |
| decoder | TFLITE | float | Qualcomm® SA8255P | 2.84 ms | 0 - 104 MB | NPU
|
| 99 |
+
| decoder | TFLITE | float | Qualcomm® QCS8450 | 2.271 ms | 0 - 220 MB | NPU
|
| 100 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 2.582 ms | 0 - 83 MB | NPU
|
| 101 |
+
| decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.239 ms | 0 - 192 MB | NPU
|
| 102 |
+
| decoder | TFLITE | float | Qualcomm® SA8295P | 2.558 ms | 0 - 43 MB | NPU
|
| 103 |
+
| encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 4.111 ms | 2 - 126 MB | NPU
|
| 104 |
+
| encoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.119 ms | 16 - 141 MB | NPU
|
| 105 |
+
| encoder | ONNX | float | Snapdragon® X2 Elite | 4.481 ms | 16 - 16 MB | NPU
|
| 106 |
+
| encoder | ONNX | float | Snapdragon® X Elite | 10.799 ms | 48 - 48 MB | NPU
|
| 107 |
+
| encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 7.491 ms | 0 - 203 MB | NPU
|
| 108 |
+
| encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 17.43 ms | 0 - 313 MB | NPU
|
| 109 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 13.562 ms | 15 - 20 MB | NPU
|
| 110 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.388 ms | 0 - 57 MB | NPU
|
| 111 |
+
| encoder | ONNX | float | Qualcomm® QCS8450 | 17.43 ms | 0 - 313 MB | NPU
|
| 112 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 12.92 ms | 15 - 20 MB | NPU
|
| 113 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.799 ms | 48 - 48 MB | NPU
|
| 114 |
+
| encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 5.119 ms | 16 - 141 MB | NPU
|
| 115 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 4.269 ms | 2 - 116 MB | NPU
|
| 116 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.263 ms | 1 - 112 MB | NPU
|
| 117 |
+
| encoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.041 ms | 2 - 2 MB | NPU
|
| 118 |
+
| encoder | QNN_DLC | float | Snapdragon® X Elite | 11.705 ms | 2 - 2 MB | NPU
|
| 119 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 7.697 ms | 2 - 194 MB | NPU
|
| 120 |
+
| encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 17.931 ms | 0 - 303 MB | NPU
|
| 121 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 13.597 ms | 2 - 13 MB | NPU
|
| 122 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.93 ms | 2 - 157 MB | NPU
|
|
|
|
|
|
|
| 123 |
| encoder | QNN_DLC | float | Qualcomm® SA8650P | 14.024 ms | 2 - 108 MB | NPU
|
| 124 |
| encoder | QNN_DLC | float | Qualcomm® SA8255P | 14.024 ms | 2 - 108 MB | NPU
|
| 125 |
+
| encoder | QNN_DLC | float | Qualcomm® QCS8450 | 17.931 ms | 0 - 303 MB | NPU
|
| 126 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 13.328 ms | 2 - 12 MB | NPU
|
| 127 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.705 ms | 2 - 2 MB | NPU
|
| 128 |
+
| encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 5.263 ms | 1 - 112 MB | NPU
|
| 129 |
+
| encoder | QNN_DLC | float | Qualcomm® SA7255P | 36.097 ms | 2 - 108 MB | NPU
|
| 130 |
+
| encoder | QNN_DLC | float | Qualcomm® SA8295P | 18.992 ms | 2 - 221 MB | NPU
|
| 131 |
+
| encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 4.067 ms | 0 - 105 MB | NPU
|
| 132 |
+
| encoder | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.007 ms | 5 - 115 MB | NPU
|
| 133 |
+
| encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.365 ms | 5 - 201 MB | NPU
|
| 134 |
+
| encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 17.221 ms | 5 - 303 MB | NPU
|
| 135 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.23 ms | 7 - 67 MB | NPU
|
| 136 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.284 ms | 7 - 9 MB | NPU
|
|
|
|
| 137 |
| encoder | TFLITE | float | Qualcomm® SA8650P | 13.479 ms | 7 - 111 MB | NPU
|
| 138 |
| encoder | TFLITE | float | Qualcomm® SA8255P | 13.479 ms | 7 - 111 MB | NPU
|
| 139 |
+
| encoder | TFLITE | float | Qualcomm® QCS8450 | 17.221 ms | 5 - 303 MB | NPU
|
| 140 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.79 ms | 6 - 66 MB | NPU
|
| 141 |
+
| encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 5.007 ms | 5 - 115 MB | NPU
|
| 142 |
+
| encoder | TFLITE | float | Qualcomm® SA8295P | 18.385 ms | 7 - 222 MB | NPU
|
|
|
|
|
|
|
|
|
|
| 143 |
|
| 144 |
## License
|
| 145 |
* The license for the original implementation of TrOCR can be found
|
release_assets.json
CHANGED
|
@@ -1,26 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
-
"qairt": "2.
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.
|
| 12 |
},
|
| 13 |
"qnn_dlc": {
|
| 14 |
"tool_versions": {
|
| 15 |
-
"qairt": "2.
|
| 16 |
},
|
| 17 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.
|
| 18 |
},
|
| 19 |
"tflite": {
|
| 20 |
"tool_versions": {
|
| 21 |
-
"qairt": "2.
|
| 22 |
},
|
| 23 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.
|
| 24 |
}
|
| 25 |
}
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.63.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"universal_assets": {
|
| 6 |
"onnx": {
|
| 7 |
"tool_versions": {
|
| 8 |
+
"qairt": "2.50.0.260828221209",
|
| 9 |
"onnx_runtime": "1.27.1"
|
| 10 |
},
|
| 11 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.63.0/trocr-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/trocr/releases/v0.63.0/trocr-qnn_dlc-float.zip"
|
| 18 |
},
|
| 19 |
"tflite": {
|
| 20 |
"tool_versions": {
|
| 21 |
+
"qairt": "2.50.0.260828221209"
|
| 22 |
},
|
| 23 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.63.0/trocr-tflite-float.zip"
|
| 24 |
}
|
| 25 |
}
|
| 26 |
}
|