Image-to-Text
PyTorch
android
qaihm-bot commited on
Commit
08cbc81
·
verified ·
1 Parent(s): 06d99fe

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (2) hide show
  1. README.md +99 -97
  2. release_assets.json +4 -4
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - android
6
  pipeline_tag: image-to-text
@@ -13,8 +13,8 @@ pipeline_tag: image-to-text
13
 
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/v0.60.0/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
 
@@ -27,23 +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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.60.0/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/v0.60.0/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/v0.60.0/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/v0.60.0/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/v0.60.0/src/qai_hub_models/models/trocr) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -51,7 +51,7 @@ See our repository for [TrOCR on GitHub](https://github.com/qualcomm/ai-hub-mode
51
 
52
  **Model Stats:**
53
  - Input resolution: 320x320
54
- - Model checkpoint: trocr-small-stage1
55
  - Model size (decoder) (float): 146 MB
56
  - Model size (encoder) (float): 87.8 MB
57
  - Number of parameters (decoder): 38.3M
@@ -60,94 +60,96 @@ 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 | 1.273 ms | 7 - 7 MB | NPU
64
- | decoder | ONNX | float | Snapdragon® X Elite | 2.072 ms | 68 - 68 MB | NPU
65
- | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.454 ms | 0 - 283 MB | NPU
66
- | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.723 ms | 1 - 219 MB | NPU
67
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 2.793 ms | 7 - 17 MB | NPU
68
- | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.112 ms | 1 - 3 MB | NPU
69
- | decoder | ONNX | float | Qualcomm® QCS8450 | 2.723 ms | 1 - 219 MB | NPU
70
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.783 ms | 7 - 16 MB | NPU
71
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.072 ms | 68 - 68 MB | NPU
72
- | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.307 ms | 0 - 195 MB | NPU
73
- | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 1.307 ms | 0 - 195 MB | NPU
74
- | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.187 ms | 2 - 179 MB | NPU
75
- | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.61 ms | 7 - 7 MB | NPU
76
- | decoder | QNN_DLC | float | Snapdragon® X Elite | 2.223 ms | 7 - 7 MB | NPU
77
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.383 ms | 0 - 274 MB | NPU
78
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.678 ms | 2 - 217 MB | NPU
79
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2.639 ms | 7 - 16 MB | NPU
80
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.17 ms | 5 - 105 MB | NPU
81
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.016 ms | 4 - 177 MB | NPU
82
- | decoder | QNN_DLC | float | Qualcomm® SA8775P | 2.886 ms | 5 - 105 MB | NPU
83
- | decoder | QNN_DLC | float | Qualcomm® SA8650P | 2.886 ms | 5 - 105 MB | NPU
84
- | decoder | QNN_DLC | float | Qualcomm® SA8255P | 2.886 ms | 5 - 105 MB | NPU
85
- | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 2.678 ms | 2 - 217 MB | NPU
86
  | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.645 ms | 7 - 16 MB | NPU
87
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.223 ms | 7 - 7 MB | NPU
88
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.25 ms | 0 - 188 MB | NPU
89
- | decoder | QNN_DLC | float | Qualcomm® SA7255P | 4.17 ms | 5 - 105 MB | NPU
90
- | decoder | QNN_DLC | float | Qualcomm® SA8295P | 2.621 ms | 0 - 41 MB | NPU
91
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.25 ms | 0 - 188 MB | NPU
92
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.152 ms | 1 - 173 MB | NPU
93
- | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.375 ms | 0 - 280 MB | NPU
94
- | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.443 ms | 0 - 218 MB | NPU
95
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2.678 ms | 0 - 84 MB | NPU
96
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.215 ms | 0 - 103 MB | NPU
97
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.952 ms | 0 - 2 MB | NPU
98
- | decoder | TFLITE | float | Qualcomm® SA8775P | 2.838 ms | 0 - 103 MB | NPU
99
- | decoder | TFLITE | float | Qualcomm® SA8650P | 2.838 ms | 0 - 103 MB | NPU
100
- | decoder | TFLITE | float | Qualcomm® SA8255P | 2.838 ms | 0 - 103 MB | NPU
101
- | decoder | TFLITE | float | Qualcomm® QCS8450 | 2.443 ms | 0 - 218 MB | NPU
102
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 2.626 ms | 0 - 83 MB | NPU
103
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.234 ms | 0 - 189 MB | NPU
104
- | decoder | TFLITE | float | Qualcomm® SA7255P | 4.215 ms | 0 - 103 MB | NPU
105
- | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.234 ms | 0 - 189 MB | NPU
106
- | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.129 ms | 0 - 177 MB | NPU
107
- | encoder | ONNX | float | Snapdragon® X2 Elite | 4.549 ms | 16 - 16 MB | NPU
108
- | encoder | ONNX | float | Snapdragon® X Elite | 11.422 ms | 47 - 47 MB | NPU
109
- | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 7.835 ms | 0 - 200 MB | NPU
110
- | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 19.866 ms | 0 - 317 MB | NPU
111
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 13.966 ms | 15 - 20 MB | NPU
112
- | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.914 ms | 0 - 57 MB | NPU
113
- | encoder | ONNX | float | Qualcomm® QCS8450 | 19.866 ms | 0 - 317 MB | NPU
114
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 13.355 ms | 15 - 19 MB | NPU
115
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.422 ms | 47 - 47 MB | NPU
116
- | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 5.282 ms | 16 - 144 MB | NPU
117
- | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 5.282 ms | 16 - 144 MB | NPU
118
- | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.167 ms | 0 - 126 MB | NPU
119
- | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.224 ms | 2 - 2 MB | NPU
120
- | encoder | QNN_DLC | float | Snapdragon® X Elite | 12.056 ms | 2 - 2 MB | NPU
121
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.007 ms | 0 - 188 MB | NPU
122
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 19.486 ms | 0 - 306 MB | NPU
123
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.267 ms | 2 - 13 MB | NPU
124
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 37.071 ms | 2 - 107 MB | NPU
125
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.286 ms | 2 - 3 MB | NPU
126
- | encoder | QNN_DLC | float | Qualcomm® SA8775P | 14.013 ms | 2 - 109 MB | NPU
127
- | encoder | QNN_DLC | float | Qualcomm® SA8650P | 14.013 ms | 2 - 109 MB | NPU
128
- | encoder | QNN_DLC | float | Qualcomm® SA8255P | 14.013 ms | 2 - 109 MB | NPU
129
- | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 19.486 ms | 0 - 306 MB | NPU
130
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 13.793 ms | 2 - 12 MB | NPU
131
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.056 ms | 2 - 2 MB | NPU
132
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 5.448 ms | 2 - 116 MB | NPU
133
- | encoder | QNN_DLC | float | Qualcomm® SA7255P | 37.071 ms | 2 - 107 MB | NPU
134
- | encoder | QNN_DLC | float | Qualcomm® SA8295P | 19.696 ms | 2 - 234 MB | NPU
135
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 5.448 ms | 2 - 116 MB | NPU
136
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.356 ms | 2 - 117 MB | NPU
137
- | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.703 ms | 0 - 189 MB | NPU
138
- | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.663 ms | 5 - 310 MB | NPU
139
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.696 ms | 7 - 67 MB | NPU
140
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 36.837 ms | 7 - 119 MB | NPU
141
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.72 ms | 7 - 9 MB | NPU
142
- | encoder | TFLITE | float | Qualcomm® SA8775P | 13.486 ms | 7 - 111 MB | NPU
143
- | encoder | TFLITE | float | Qualcomm® SA8650P | 13.486 ms | 7 - 111 MB | NPU
144
- | encoder | TFLITE | float | Qualcomm® SA8255P | 13.486 ms | 7 - 111 MB | NPU
145
- | encoder | TFLITE | float | Qualcomm® QCS8450 | 19.663 ms | 5 - 310 MB | NPU
146
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 13.352 ms | 7 - 66 MB | NPU
147
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 5.202 ms | 7 - 120 MB | NPU
148
- | encoder | TFLITE | float | Qualcomm® SA7255P | 36.837 ms | 7 - 119 MB | NPU
149
- | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 5.202 ms | 7 - 120 MB | NPU
150
- | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.118 ms | 7 - 111 MB | NPU
 
 
151
 
152
  ## License
153
  * The license for the original implementation of TrOCR can be found
@@ -155,7 +157,7 @@ See our repository for [TrOCR on GitHub](https://github.com/qualcomm/ai-hub-mode
155
 
156
  ## References
157
  * [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282)
158
- * [Source Model Implementation](https://huggingface.co/microsoft/trocr-small-stage1)
159
 
160
  ## Community
161
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 
1
  ---
2
  library_name: pytorch
3
+ license: mit
4
  tags:
5
  - android
6
  pipeline_tag: image-to-text
 
13
 
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/v0.61.0/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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/src/qai_hub_models/models/trocr) for usage instructions.
47
 
48
  ## Model Details
49
 
 
51
 
52
  **Model Stats:**
53
  - Input resolution: 320x320
54
+ - Model checkpoint: trocr-small-handwritten
55
  - Model size (decoder) (float): 146 MB
56
  - Model size (encoder) (float): 87.8 MB
57
  - Number of parameters (decoder): 38.3M
 
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 | 1.275 ms | 7 - 7 MB | NPU
64
+ | decoder | ONNX | float | Snapdragon® X Elite | 2.076 ms | 68 - 68 MB | NPU
65
+ | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.469 ms | 0 - 280 MB | NPU
66
+ | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.753 ms | 1 - 219 MB | NPU
67
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 2.76 ms | 7 - 17 MB | NPU
68
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.327 ms | 1 - 3 MB | NPU
69
+ | decoder | ONNX | float | Qualcomm® QCS8450 | 2.753 ms | 1 - 219 MB | NPU
70
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 2.775 ms | 7 - 17 MB | NPU
71
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.076 ms | 68 - 68 MB | NPU
72
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.286 ms | 0 - 192 MB | NPU
73
+ | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 1.286 ms | 0 - 192 MB | NPU
74
+ | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.183 ms | 2 - 179 MB | NPU
75
+ | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 1.636 ms | 7 - 7 MB | NPU
76
+ | decoder | QNN_DLC | float | Snapdragon® X Elite | 2.26 ms | 7 - 7 MB | NPU
77
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.397 ms | 0 - 277 MB | NPU
78
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.678 ms | 2 - 218 MB | NPU
79
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2.68 ms | 7 - 16 MB | NPU
80
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.174 ms | 5 - 105 MB | NPU
81
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.007 ms | 1 - 2 MB | NPU
82
+ | decoder | QNN_DLC | float | Qualcomm® SA8775P | 2.855 ms | 5 - 107 MB | NPU
83
+ | decoder | QNN_DLC | float | Qualcomm® SA8650P | 2.855 ms | 5 - 107 MB | NPU
84
+ | decoder | QNN_DLC | float | Qualcomm® SA8255P | 2.855 ms | 5 - 107 MB | NPU
85
+ | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 2.678 ms | 2 - 218 MB | NPU
86
  | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.645 ms | 7 - 16 MB | NPU
87
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.26 ms | 7 - 7 MB | NPU
88
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.271 ms | 0 - 186 MB | NPU
89
+ | decoder | QNN_DLC | float | Qualcomm® SA7255P | 4.174 ms | 5 - 105 MB | NPU
90
+ | decoder | QNN_DLC | float | Qualcomm® SA8295P | 2.635 ms | 0 - 42 MB | NPU
91
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.271 ms | 0 - 186 MB | NPU
92
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.145 ms | 1 - 175 MB | NPU
93
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.386 ms | 0 - 281 MB | NPU
94
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 2.447 ms | 0 - 217 MB | NPU
95
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2.682 ms | 0 - 84 MB | NPU
96
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.201 ms | 0 - 104 MB | NPU
97
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.983 ms | 0 - 2 MB | NPU
98
+ | decoder | TFLITE | float | Qualcomm® SA8775P | 2.85 ms | 0 - 103 MB | NPU
99
+ | decoder | TFLITE | float | Qualcomm® SA8650P | 2.85 ms | 0 - 103 MB | NPU
100
+ | decoder | TFLITE | float | Qualcomm® SA8255P | 2.85 ms | 0 - 103 MB | NPU
101
+ | decoder | TFLITE | float | Qualcomm® QCS8450 | 2.447 ms | 0 - 217 MB | NPU
102
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 2.588 ms | 0 - 83 MB | NPU
103
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.265 ms | 0 - 191 MB | NPU
104
+ | decoder | TFLITE | float | Qualcomm® SA7255P | 4.201 ms | 0 - 104 MB | NPU
105
+ | decoder | TFLITE | float | Qualcomm® SA8295P | 2.679 ms | 0 - 42 MB | NPU
106
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.265 ms | 0 - 191 MB | NPU
107
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.145 ms | 0 - 176 MB | NPU
108
+ | encoder | ONNX | float | Snapdragon® X2 Elite | 4.57 ms | 16 - 16 MB | NPU
109
+ | encoder | ONNX | float | Snapdragon® X Elite | 11.222 ms | 48 - 48 MB | NPU
110
+ | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 7.819 ms | 1 - 200 MB | NPU
111
+ | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 19.732 ms | 16 - 334 MB | NPU
112
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 13.977 ms | 15 - 20 MB | NPU
113
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.913 ms | 0 - 57 MB | NPU
114
+ | encoder | ONNX | float | Qualcomm® QCS8450 | 19.732 ms | 16 - 334 MB | NPU
115
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 13.459 ms | 15 - 19 MB | NPU
116
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.222 ms | 48 - 48 MB | NPU
117
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 5.27 ms | 16 - 142 MB | NPU
118
+ | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 5.27 ms | 16 - 142 MB | NPU
119
+ | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.17 ms | 0 - 126 MB | NPU
120
+ | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.129 ms | 2 - 2 MB | NPU
121
+ | encoder | QNN_DLC | float | Snapdragon® X Elite | 12.049 ms | 2 - 2 MB | NPU
122
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.023 ms | 2 - 191 MB | NPU
123
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 19.505 ms | 0 - 308 MB | NPU
124
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.315 ms | 2 - 13 MB | NPU
125
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 37.105 ms | 2 - 107 MB | NPU
126
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.288 ms | 2 - 23 MB | NPU
127
+ | encoder | QNN_DLC | float | Qualcomm® SA8775P | 13.982 ms | 2 - 109 MB | NPU
128
+ | encoder | QNN_DLC | float | Qualcomm® SA8650P | 13.982 ms | 2 - 109 MB | NPU
129
+ | encoder | QNN_DLC | float | Qualcomm® SA8255P | 13.982 ms | 2 - 109 MB | NPU
130
+ | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 19.505 ms | 0 - 308 MB | NPU
131
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 13.807 ms | 2 - 12 MB | NPU
132
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.049 ms | 2 - 2 MB | NPU
133
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 5.444 ms | 2 - 115 MB | NPU
134
+ | encoder | QNN_DLC | float | Qualcomm® SA7255P | 37.105 ms | 2 - 107 MB | NPU
135
+ | encoder | QNN_DLC | float | Qualcomm® SA8295P | 19.684 ms | 2 - 234 MB | NPU
136
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 5.444 ms | 2 - 115 MB | NPU
137
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.356 ms | 2 - 116 MB | NPU
138
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 7.708 ms | 6 - 198 MB | NPU
139
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.617 ms | 7 - 312 MB | NPU
140
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.99 ms | 7 - 67 MB | NPU
141
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 36.844 ms | 7 - 119 MB | NPU
142
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.684 ms | 7 - 9 MB | NPU
143
+ | encoder | TFLITE | float | Qualcomm® SA8775P | 13.488 ms | 7 - 110 MB | NPU
144
+ | encoder | TFLITE | float | Qualcomm® SA8650P | 13.488 ms | 7 - 110 MB | NPU
145
+ | encoder | TFLITE | float | Qualcomm® SA8255P | 13.488 ms | 7 - 110 MB | NPU
146
+ | encoder | TFLITE | float | Qualcomm® QCS8450 | 19.617 ms | 7 - 312 MB | NPU
147
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 13.343 ms | 6 - 66 MB | NPU
148
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 5.206 ms | 5 - 118 MB | NPU
149
+ | encoder | TFLITE | float | Qualcomm® SA7255P | 36.844 ms | 7 - 119 MB | NPU
150
+ | encoder | TFLITE | float | Qualcomm® SA8295P | 19.074 ms | 7 - 237 MB | NPU
151
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 5.206 ms | 5 - 118 MB | NPU
152
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.099 ms | 6 - 113 MB | NPU
153
 
154
  ## License
155
  * The license for the original implementation of TrOCR can be found
 
157
 
158
  ## References
159
  * [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://arxiv.org/abs/2109.10282)
160
+ * [Source Model Implementation](https://huggingface.co/microsoft/trocr-small-handwritten)
161
 
162
  ## Community
163
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
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/v0.60.0/trocr-onnx-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/v0.60.0/trocr-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.60.0/trocr-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.61.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
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/v0.61.0/trocr-onnx-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/v0.61.0/trocr-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/trocr/releases/v0.61.0/trocr-tflite-float.zip"
24
  }
25
  }
26
  }