Image-to-Text
PyTorch
android
qaihm-bot commited on
Commit
a20b7af
·
verified ·
1 Parent(s): b6e8100

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +88 -82
  2. release_assets.json +4 -4
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-stage1).
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/v0.57.3/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
 
@@ -27,23 +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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.57.3/trocr-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.57.3/trocr-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.57.3/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/v0.57.3/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/v0.57.3/src/qai_hub_models/models/trocr) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -60,84 +60,90 @@ 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® X2 Elite | 1.27 ms | 205 - 205 MB | NPU
64
- | decoder | ONNX | float | Snapdragon® X Elite | 2.106 ms | 174 - 174 MB | NPU
65
- | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.5 ms | 0 - 272 MB | NPU
66
- | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.738 ms | 1 - 209 MB | NPU
67
- | decoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.124 ms | 1 - 4 MB | NPU
68
- | decoder | ONNX | float | Qualcomm® QCS8450 | 2.738 ms | 1 - 209 MB | NPU
69
- | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 1.302 ms | 0 - 192 MB | NPU
70
- | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.206 ms | 1 - 173 MB | NPU
71
- | decoder | ONNX | float | Qualcomm® QCS9075 | 2.684 ms | 7 - 51 MB | NPU
72
- | decoder | ONNX | float | Qualcomm® QCS8750 | 1.302 ms | 0 - 192 MB | NPU
73
- | decoder | ONNX | float | Qualcomm® QCS7181 | 2.106 ms | 174 - 174 MB | NPU
74
- | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.636 ms | 7 - 7 MB | NPU
75
- | decoder | QNN_DLC | float | Snapdragon® X Elite | 2.229 ms | 7 - 7 MB | NPU
76
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.367 ms | 0 - 274 MB | NPU
77
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.663 ms | 2 - 217 MB | NPU
78
- | decoder | QNN_DLC | float | Qualcomm® QCS8275 | 4.237 ms | 5 - 105 MB | NPU
79
- | decoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.025 ms | 3 - 174 MB | NPU
80
- | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 2.663 ms | 2 - 217 MB | NPU
81
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.237 ms | 0 - 187 MB | NPU
82
- | decoder | QNN_DLC | float | Qualcomm® SA8295P | 2.606 ms | 7 - 49 MB | NPU
83
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.164 ms | 1 - 173 MB | NPU
84
- | decoder | QNN_DLC | float | Qualcomm® SA7255P | 4.237 ms | 5 - 105 MB | NPU
85
- | decoder | QNN_DLC | float | Qualcomm® QCS9075 | 2.573 ms | 7 - 16 MB | NPU
86
- | decoder | QNN_DLC | float | Qualcomm® QCS8750 | 1.237 ms | 0 - 187 MB | NPU
87
- | decoder | QNN_DLC | float | Qualcomm® QCS7181 | 2.229 ms | 7 - 7 MB | NPU
 
 
 
88
  | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.381 ms | 0 - 280 MB | NPU
89
- | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.439 ms | 0 - 217 MB | NPU
90
- | decoder | TFLITE | float | Qualcomm® QCS8275 | 4.249 ms | 0 - 104 MB | NPU
91
- | decoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.987 ms | 0 - 2 MB | NPU
92
- | decoder | TFLITE | float | Qualcomm® SA8775P | 8.85 ms | 7 - 25 MB | GPU
93
- | decoder | TFLITE | float | Qualcomm® SA8650P | 8.85 ms | 7 - 25 MB | GPU
94
- | decoder | TFLITE | float | Qualcomm® SA8255P | 8.85 ms | 7 - 25 MB | GPU
95
- | decoder | TFLITE | float | Qualcomm® QCS8450 | 2.439 ms | 0 - 217 MB | NPU
96
- | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.237 ms | 0 - 189 MB | NPU
97
- | decoder | TFLITE | float | Qualcomm® SA8295P | 2.666 ms | 0 - 42 MB | NPU
98
- | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.145 ms | 0 - 175 MB | NPU
99
- | decoder | TFLITE | float | Qualcomm® SA7255P | 4.249 ms | 0 - 104 MB | NPU
100
- | decoder | TFLITE | float | Qualcomm® QCS9075 | 2.581 ms | 0 - 83 MB | NPU
101
- | decoder | TFLITE | float | Qualcomm® QCS8750 | 1.237 ms | 0 - 189 MB | NPU
102
- | encoder | ONNX | float | Snapdragon® X2 Elite | 5.484 ms | 211 - 211 MB | NPU
103
- | encoder | ONNX | float | Snapdragon® X Elite | 11.431 ms | 180 - 180 MB | NPU
104
- | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 7.839 ms | 16 - 205 MB | NPU
105
- | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 20.027 ms | 16 - 322 MB | NPU
106
- | encoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 10.915 ms | 0 - 59 MB | NPU
107
- | encoder | ONNX | float | Qualcomm® QCS8450 | 20.027 ms | 16 - 322 MB | NPU
108
- | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 5.294 ms | 16 - 141 MB | NPU
109
- | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.13 ms | 2 - 124 MB | NPU
110
- | encoder | ONNX | float | Qualcomm® QCS9075 | 14.176 ms | 15 - 60 MB | NPU
111
- | encoder | ONNX | float | Qualcomm® QCS8750 | 5.294 ms | 16 - 141 MB | NPU
112
- | encoder | ONNX | float | Qualcomm® QCS7181 | 11.431 ms | 180 - 180 MB | NPU
113
- | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.178 ms | 2 - 2 MB | NPU
114
- | encoder | QNN_DLC | float | Snapdragon® X Elite | 12.181 ms | 2 - 2 MB | NPU
115
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.016 ms | 0 - 190 MB | NPU
116
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 19.436 ms | 0 - 306 MB | NPU
117
- | encoder | QNN_DLC | float | Qualcomm® QCS8275 | 37.03 ms | 2 - 107 MB | NPU
118
- | encoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 11.295 ms | 2 - 170 MB | NPU
119
- | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 19.436 ms | 0 - 306 MB | NPU
120
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 5.448 ms | 2 - 113 MB | NPU
121
- | encoder | QNN_DLC | float | Qualcomm® SA8295P | 19.688 ms | 2 - 233 MB | NPU
122
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.328 ms | 2 - 116 MB | NPU
123
- | encoder | QNN_DLC | float | Qualcomm® SA7255P | 37.03 ms | 2 - 107 MB | NPU
124
- | encoder | QNN_DLC | float | Qualcomm® QCS9075 | 15.108 ms | 2 - 12 MB | NPU
125
- | encoder | QNN_DLC | float | Qualcomm® QCS8750 | 5.448 ms | 2 - 113 MB | NPU
126
- | encoder | QNN_DLC | float | Qualcomm® QCS7181 | 12.181 ms | 2 - 2 MB | NPU
 
 
 
127
  | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.705 ms | 3 - 195 MB | NPU
128
- | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.541 ms | 7 - 311 MB | NPU
129
- | encoder | TFLITE | float | Qualcomm® QCS8275 | 36.805 ms | 7 - 119 MB | NPU
130
- | encoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 10.741 ms | 7 - 9 MB | NPU
131
- | encoder | TFLITE | float | Qualcomm® SA8775P | 122.908 ms | 6 - 34 MB | GPU
132
- | encoder | TFLITE | float | Qualcomm® SA8650P | 122.908 ms | 6 - 34 MB | GPU
133
- | encoder | TFLITE | float | Qualcomm® SA8255P | 122.908 ms | 6 - 34 MB | GPU
134
- | encoder | TFLITE | float | Qualcomm® QCS8450 | 19.541 ms | 7 - 311 MB | NPU
135
- | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 5.202 ms | 6 - 118 MB | NPU
136
- | encoder | TFLITE | float | Qualcomm® SA8295P | 19.12 ms | 7 - 236 MB | NPU
137
- | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.102 ms | 0 - 105 MB | NPU
138
- | encoder | TFLITE | float | Qualcomm® SA7255P | 36.805 ms | 7 - 119 MB | NPU
139
- | encoder | TFLITE | float | Qualcomm® QCS9075 | 13.921 ms | 5 - 65 MB | NPU
140
- | encoder | TFLITE | float | Qualcomm® QCS8750 | 5.202 ms | 6 - 118 MB | NPU
141
 
142
  ## License
143
  * 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-stage1).
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/v0.58.0/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.58.0/trocr-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.58.0/trocr-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.58.0/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/v0.58.0/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/v0.58.0/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® X2 Elite | 1.259 ms | 7 - 7 MB | NPU
64
+ | decoder | ONNX | float | Snapdragon® X Elite | 2.1 ms | 68 - 68 MB | NPU
65
+ | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.449 ms | 0 - 282 MB | NPU
66
+ | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.735 ms | 1 - 218 MB | NPU
67
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.112 ms | 1 - 3 MB | NPU
68
+ | decoder | ONNX | float | Qualcomm® QCS8450 | 2.735 ms | 1 - 218 MB | NPU
69
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.74 ms | 7 - 16 MB | NPU
70
+ | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.182 ms | 2 - 179 MB | NPU
71
+ | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 1.3 ms | 0 - 189 MB | NPU
72
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.3 ms | 0 - 189 MB | NPU
73
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.1 ms | 68 - 68 MB | NPU
74
+ | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.556 ms | 7 - 7 MB | NPU
75
+ | decoder | QNN_DLC | float | Snapdragon® X Elite | 2.208 ms | 7 - 7 MB | NPU
76
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.424 ms | 0 - 278 MB | NPU
77
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.672 ms | 2 - 216 MB | NPU
78
+ | decoder | QNN_DLC | float | Qualcomm® QCS8275 | 4.137 ms | 5 - 106 MB | NPU
79
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.012 ms | 1 - 2 MB | NPU
80
+ | decoder | QNN_DLC | float | Qualcomm® SA8775P | 2.861 ms | 5 - 107 MB | NPU
81
+ | decoder | QNN_DLC | float | Qualcomm® SA8650P | 2.861 ms | 5 - 107 MB | NPU
82
+ | decoder | QNN_DLC | float | Qualcomm® SA8255P | 2.861 ms | 5 - 107 MB | NPU
83
+ | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 2.672 ms | 2 - 216 MB | NPU
84
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.859 ms | 7 - 16 MB | NPU
85
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.158 ms | 1 - 172 MB | NPU
86
+ | decoder | QNN_DLC | float | Qualcomm® SA7255P | 4.137 ms | 5 - 106 MB | NPU
87
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.247 ms | 0 - 187 MB | NPU
88
+ | decoder | QNN_DLC | float | Qualcomm® SA8295P | 2.558 ms | 0 - 42 MB | NPU
89
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.247 ms | 0 - 187 MB | NPU
90
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.208 ms | 7 - 7 MB | NPU
91
  | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.381 ms | 0 - 280 MB | NPU
92
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.456 ms | 0 - 217 MB | NPU
93
+ | decoder | TFLITE | float | Qualcomm® QCS8275 | 12.741 ms | 7 - 22 MB | GPU
94
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.95 ms | 0 - 2 MB | NPU
95
+ | decoder | TFLITE | float | Qualcomm® SA8775P | 2.847 ms | 0 - 103 MB | NPU
96
+ | decoder | TFLITE | float | Qualcomm® SA8650P | 2.847 ms | 0 - 103 MB | NPU
97
+ | decoder | TFLITE | float | Qualcomm® SA8255P | 2.847 ms | 0 - 103 MB | NPU
98
+ | decoder | TFLITE | float | Qualcomm® QCS8450 | 2.456 ms | 0 - 217 MB | NPU
99
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 2.779 ms | 0 - 83 MB | NPU
100
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.136 ms | 0 - 171 MB | NPU
101
+ | decoder | TFLITE | float | Qualcomm® SA7255P | 12.741 ms | 7 - 22 MB | GPU
102
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.266 ms | 0 - 190 MB | NPU
103
+ | decoder | TFLITE | float | Qualcomm® SA8295P | 2.597 ms | 0 - 44 MB | NPU
104
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.266 ms | 0 - 190 MB | NPU
105
+ | encoder | ONNX | float | Snapdragon® X2 Elite | 4.557 ms | 16 - 16 MB | NPU
106
+ | encoder | ONNX | float | Snapdragon® X Elite | 11.3 ms | 48 - 48 MB | NPU
107
+ | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 7.834 ms | 0 - 199 MB | NPU
108
+ | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 19.787 ms | 0 - 315 MB | NPU
109
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.93 ms | 0 - 269 MB | NPU
110
+ | encoder | ONNX | float | Qualcomm® QCS8450 | 19.787 ms | 0 - 315 MB | NPU
111
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 13.736 ms | 15 - 19 MB | NPU
112
+ | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.149 ms | 0 - 124 MB | NPU
113
+ | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 5.304 ms | 16 - 139 MB | NPU
114
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 5.304 ms | 16 - 139 MB | NPU
115
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.3 ms | 48 - 48 MB | NPU
116
+ | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.137 ms | 2 - 2 MB | NPU
117
+ | encoder | QNN_DLC | float | Snapdragon® X Elite | 12.101 ms | 2 - 2 MB | NPU
118
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.005 ms | 2 - 192 MB | NPU
119
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 19.346 ms | 2 - 309 MB | NPU
120
+ | encoder | QNN_DLC | float | Qualcomm® QCS8275 | 37.051 ms | 2 - 107 MB | NPU
121
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.262 ms | 2 - 4 MB | NPU
122
+ | encoder | QNN_DLC | float | Qualcomm® SA8775P | 14.018 ms | 2 - 109 MB | NPU
123
+ | encoder | QNN_DLC | float | Qualcomm® SA8650P | 14.018 ms | 2 - 109 MB | NPU
124
+ | encoder | QNN_DLC | float | Qualcomm® SA8255P | 14.018 ms | 2 - 109 MB | NPU
125
+ | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 19.346 ms | 2 - 309 MB | NPU
126
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 14.22 ms | 4 - 14 MB | NPU
127
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.351 ms | 2 - 115 MB | NPU
128
+ | encoder | QNN_DLC | float | Qualcomm® SA7255P | 37.051 ms | 2 - 107 MB | NPU
129
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 5.44 ms | 2 - 116 MB | NPU
130
+ | encoder | QNN_DLC | float | Qualcomm® SA8295P | 19.681 ms | 2 - 235 MB | NPU
131
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 5.44 ms | 2 - 116 MB | NPU
132
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.101 ms | 2 - 2 MB | NPU
133
  | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.705 ms | 3 - 195 MB | NPU
134
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.56 ms | 7 - 312 MB | NPU
135
+ | encoder | TFLITE | float | Qualcomm® QCS8275 | 36.827 ms | 7 - 119 MB | NPU
136
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.673 ms | 7 - 9 MB | NPU
137
+ | encoder | TFLITE | float | Qualcomm® SA8775P | 13.49 ms | 7 - 111 MB | NPU
138
+ | encoder | TFLITE | float | Qualcomm® SA8650P | 13.49 ms | 7 - 111 MB | NPU
139
+ | encoder | TFLITE | float | Qualcomm® SA8255P | 13.49 ms | 7 - 111 MB | NPU
140
+ | encoder | TFLITE | float | Qualcomm® QCS8450 | 19.56 ms | 7 - 312 MB | NPU
141
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 13.235 ms | 6 - 65 MB | NPU
142
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.119 ms | 0 - 104 MB | NPU
143
+ | encoder | TFLITE | float | Qualcomm® SA7255P | 36.827 ms | 7 - 119 MB | NPU
144
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 5.202 ms | 6 - 119 MB | NPU
145
+ | encoder | TFLITE | float | Qualcomm® SA8295P | 19.106 ms | 7 - 237 MB | NPU
146
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 5.202 ms | 6 - 119 MB | NPU
147
 
148
  ## License
149
  * The license for the original implementation of TrOCR can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.57.3/trocr-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.57.3/trocr-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.57.3/trocr-onnx-float.zip"
25
  }
26
  }
27
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.58.0/trocr-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.58.0/trocr-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.58.0/trocr-onnx-float.zip"
25
  }
26
  }
27
  }