Hugging Face's logo

qualcomm
/
XLSR

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
c789cf0
·
verified ·
1 Parent(s): 22f50dd

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +73 -73
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-to-image
14
  XLSR is designed for lightweight real-time upscaling of images.
15
 
16
  This is based on the implementation of XLSR found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/xlsr).
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/main/qai_hub_models/models/xlsr) 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
 
@@ -27,26 +27,26 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.48.0/xlsr-onnx-float.zip)
31
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.48.0/xlsr-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.48.0/xlsr-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.48.0/xlsr-qnn_dlc-w8a8.zip)
34
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.48.0/xlsr-tflite-float.zip)
35
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.48.0/xlsr-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[XLSR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/xlsr)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/xlsr) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [XLSR on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/xlsr) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -62,73 +62,73 @@ See our repository for [XLSR on GitHub](https://github.com/qualcomm/ai-hub-model
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | XLSR | ONNX | float | Snapdragon® X2 Elite | 0.438 ms | 6 - 6 MB | NPU
66
- | XLSR | ONNX | float | Snapdragon® X Elite | 1.059 ms | 8 - 8 MB | NPU
67
- | XLSR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.675 ms | 0 - 28 MB | NPU
68
- | XLSR | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.936 ms | 0 - 67 MB | NPU
69
- | XLSR | ONNX | float | Qualcomm® QCS9075 | 1.243 ms | 6 - 9 MB | NPU
70
- | XLSR | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.51 ms | 0 - 19 MB | NPU
71
- | XLSR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.426 ms | 0 - 22 MB | NPU
72
- | XLSR | ONNX | w8a8 | Snapdragon® X2 Elite | 0.248 ms | 1 - 1 MB | NPU
73
- | XLSR | ONNX | w8a8 | Snapdragon® X Elite | 0.651 ms | 3 - 3 MB | NPU
74
- | XLSR | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.368 ms | 0 - 29 MB | NPU
75
- | XLSR | ONNX | w8a8 | Qualcomm® QCS6490 | 11.878 ms | 19 - 22 MB | CPU
76
- | XLSR | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.549 ms | 0 - 2 MB | NPU
77
- | XLSR | ONNX | w8a8 | Qualcomm® QCS9075 | 0.692 ms | 0 - 3 MB | NPU
78
- | XLSR | ONNX | w8a8 | Qualcomm® QCM6690 | 8.416 ms | 17 - 24 MB | CPU
 
79
  | XLSR | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.261 ms | 0 - 24 MB | NPU
80
- | XLSR | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 6.094 ms | 18 - 25 MB | CPU
81
- | XLSR | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.244 ms | 0 - 23 MB | NPU
82
- | XLSR | QNN_DLC | float | Snapdragon® X2 Elite | 0.414 ms | 0 - 0 MB | NPU
83
- | XLSR | QNN_DLC | float | Snapdragon® X Elite | 0.885 ms | 0 - 0 MB | NPU
84
- | XLSR | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.475 ms | 0 - 29 MB | NPU
85
- | XLSR | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2.166 ms | 0 - 23 MB | NPU
86
- | XLSR | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.771 ms | 0 - 68 MB | NPU
87
- | XLSR | QNN_DLC | float | Qualcomm® SA8775P | 1.145 ms | 0 - 22 MB | NPU
88
- | XLSR | QNN_DLC | float | Qualcomm® QCS9075 | 1.134 ms | 0 - 5 MB | NPU
89
- | XLSR | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.05 ms | 0 - 30 MB | NPU
90
- | XLSR | QNN_DLC | float | Qualcomm® SA7255P | 2.166 ms | 0 - 23 MB | NPU
91
- | XLSR | QNN_DLC | float | Qualcomm® SA8295P | 1.354 ms | 0 - 18 MB | NPU
92
- | XLSR | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.362 ms | 0 - 21 MB | NPU
93
- | XLSR | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.317 ms | 0 - 24 MB | NPU
94
- | XLSR | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.263 ms | 0 - 0 MB | NPU
95
- | XLSR | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.483 ms | 0 - 0 MB | NPU
96
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.249 ms | 0 - 27 MB | NPU
97
- | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.421 ms | 0 - 2 MB | NPU
98
- | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.906 ms | 0 - 20 MB | NPU
99
- | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.372 ms | 0 - 2 MB | NPU
100
- | XLSR | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.578 ms | 0 - 21 MB | NPU
101
  | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.526 ms | 0 - 2 MB | NPU
102
- | XLSR | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1.682 ms | 0 - 18 MB | NPU
103
- | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.53 ms | 0 - 28 MB | NPU
104
- | XLSR | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.906 ms | 0 - 20 MB | NPU
105
- | XLSR | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.788 ms | 0 - 17 MB | NPU
106
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.197 ms | 0 - 23 MB | NPU
107
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.397 ms | 0 - 18 MB | NPU
108
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.162 ms | 0 - 21 MB | NPU
109
- | XLSR | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.459 ms | 0 - 29 MB | NPU
110
- | XLSR | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.798 ms | 3 - 23 MB | NPU
111
- | XLSR | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.229 ms | 0 - 67 MB | NPU
112
- | XLSR | TFLITE | float | Qualcomm® SA8775P | 2.673 ms | 0 - 21 MB | NPU
113
- | XLSR | TFLITE | float | Qualcomm® QCS9075 | 2.614 ms | 3 - 8 MB | NPU
114
- | XLSR | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.564 ms | 0 - 30 MB | NPU
115
- | XLSR | TFLITE | float | Qualcomm® SA7255P | 4.798 ms | 3 - 23 MB | NPU
116
- | XLSR | TFLITE | float | Qualcomm® SA8295P | 3.364 ms | 0 - 17 MB | NPU
117
- | XLSR | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.001 ms | 0 - 20 MB | NPU
118
  | XLSR | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.827 ms | 0 - 22 MB | NPU
119
- | XLSR | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.237 ms | 0 - 29 MB | NPU
120
- | XLSR | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.122 ms | 0 - 3 MB | NPU
121
- | XLSR | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.896 ms | 0 - 21 MB | NPU
122
- | XLSR | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.388 ms | 0 - 60 MB | NPU
123
- | XLSR | TFLITE | w8a8 | Qualcomm® SA8775P | 0.617 ms | 0 - 21 MB | NPU
124
- | XLSR | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.586 ms | 0 - 3 MB | NPU
125
- | XLSR | TFLITE | w8a8 | Qualcomm® QCM6690 | 1.604 ms | 0 - 19 MB | NPU
126
- | XLSR | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.532 ms | 0 - 30 MB | NPU
127
- | XLSR | TFLITE | w8a8 | Qualcomm® SA7255P | 0.896 ms | 0 - 21 MB | NPU
128
- | XLSR | TFLITE | w8a8 | Qualcomm® SA8295P | 0.779 ms | 0 - 17 MB | NPU
129
- | XLSR | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.213 ms | 0 - 24 MB | NPU
130
- | XLSR | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.399 ms | 0 - 19 MB | NPU
131
- | XLSR | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.163 ms | 0 - 22 MB | NPU
 
 
 
 
 
 
 
 
 
132
 
133
  ## License
134
  * The license for the original implementation of XLSR can be found
 
14
  XLSR is designed for lightweight real-time upscaling of images.
15
 
16
  This is based on the implementation of XLSR found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/xlsr).
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/tree/v0.49.1/qai_hub_models/models/xlsr) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.49.1/xlsr-onnx-float.zip)
31
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.49.1/xlsr-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.49.1/xlsr-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.49.1/xlsr-qnn_dlc-w8a8.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.49.1/xlsr-tflite-float.zip)
35
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.49.1/xlsr-tflite-w8a8.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[XLSR on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/xlsr)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/xlsr) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [XLSR on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/xlsr) for usage instructions.
50
 
51
  ## Model Details
52
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | XLSR | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.435 ms | 0 - 22 MB | NPU
66
+ | XLSR | ONNX | float | Snapdragon® X2 Elite | 0.443 ms | 7 - 7 MB | NPU
67
+ | XLSR | ONNX | float | Snapdragon® X Elite | 1.064 ms | 8 - 8 MB | NPU
68
+ | XLSR | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.643 ms | 0 - 29 MB | NPU
69
+ | XLSR | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.965 ms | 0 - 10 MB | NPU
70
+ | XLSR | ONNX | float | Qualcomm® QCS9075 | 1.246 ms | 6 - 9 MB | NPU
71
+ | XLSR | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.54 ms | 0 - 23 MB | NPU
72
+ | XLSR | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.245 ms | 0 - 23 MB | NPU
73
+ | XLSR | ONNX | w8a8 | Snapdragon® X2 Elite | 0.241 ms | 1 - 1 MB | NPU
74
+ | XLSR | ONNX | w8a8 | Snapdragon® X Elite | 0.652 ms | 3 - 3 MB | NPU
75
+ | XLSR | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.348 ms | 0 - 29 MB | NPU
76
+ | XLSR | ONNX | w8a8 | Qualcomm® QCS6490 | 12.179 ms | 20 - 22 MB | CPU
77
+ | XLSR | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.547 ms | 0 - 2 MB | NPU
78
+ | XLSR | ONNX | w8a8 | Qualcomm® QCS9075 | 0.691 ms | 0 - 3 MB | NPU
79
+ | XLSR | ONNX | w8a8 | Qualcomm® QCM6690 | 8.48 ms | 19 - 25 MB | CPU
80
  | XLSR | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.261 ms | 0 - 24 MB | NPU
81
+ | XLSR | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 6.158 ms | 19 - 25 MB | CPU
82
+ | XLSR | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.327 ms | 0 - 25 MB | NPU
83
+ | XLSR | QNN_DLC | float | Snapdragon® X2 Elite | 0.402 ms | 0 - 0 MB | NPU
84
+ | XLSR | QNN_DLC | float | Snapdragon® X Elite | 0.893 ms | 0 - 0 MB | NPU
85
+ | XLSR | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.465 ms | 0 - 29 MB | NPU
86
+ | XLSR | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2.158 ms | 0 - 21 MB | NPU
87
+ | XLSR | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.783 ms | 0 - 1 MB | NPU
88
+ | XLSR | QNN_DLC | float | Qualcomm® SA8775P | 1.144 ms | 0 - 22 MB | NPU
89
+ | XLSR | QNN_DLC | float | Qualcomm® QCS9075 | 1.115 ms | 0 - 5 MB | NPU
90
+ | XLSR | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.044 ms | 0 - 30 MB | NPU
91
+ | XLSR | QNN_DLC | float | Qualcomm® SA7255P | 2.158 ms | 0 - 21 MB | NPU
92
+ | XLSR | QNN_DLC | float | Qualcomm® SA8295P | 1.387 ms | 0 - 18 MB | NPU
93
+ | XLSR | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.361 ms | 0 - 25 MB | NPU
94
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.167 ms | 0 - 21 MB | NPU
95
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.254 ms | 0 - 0 MB | NPU
96
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.499 ms | 0 - 0 MB | NPU
97
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.248 ms | 0 - 27 MB | NPU
98
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 1.402 ms | 0 - 2 MB | NPU
99
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.929 ms | 0 - 21 MB | NPU
100
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.396 ms | 0 - 2 MB | NPU
101
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.575 ms | 0 - 21 MB | NPU
102
  | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 0.526 ms | 0 - 2 MB | NPU
103
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1.658 ms | 0 - 18 MB | NPU
104
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.52 ms | 0 - 29 MB | NPU
105
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.929 ms | 0 - 21 MB | NPU
106
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.779 ms | 0 - 17 MB | NPU
107
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.196 ms | 0 - 23 MB | NPU
108
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.402 ms | 0 - 18 MB | NPU
 
 
 
 
 
 
 
 
 
 
109
  | XLSR | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.827 ms | 0 - 22 MB | NPU
110
+ | XLSR | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.459 ms | 0 - 29 MB | NPU
111
+ | XLSR | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.825 ms | 3 - 24 MB | NPU
112
+ | XLSR | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.233 ms | 0 - 1 MB | NPU
113
+ | XLSR | TFLITE | float | Qualcomm® SA8775P | 2.708 ms | 0 - 21 MB | NPU
114
+ | XLSR | TFLITE | float | Qualcomm® QCS9075 | 2.613 ms | 1 - 6 MB | NPU
115
+ | XLSR | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.564 ms | 0 - 29 MB | NPU
116
+ | XLSR | TFLITE | float | Qualcomm® SA7255P | 4.825 ms | 3 - 24 MB | NPU
117
+ | XLSR | TFLITE | float | Qualcomm® SA8295P | 3.343 ms | 0 - 17 MB | NPU
118
+ | XLSR | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.002 ms | 0 - 24 MB | NPU
119
+ | XLSR | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.16 ms | 0 - 22 MB | NPU
120
+ | XLSR | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.236 ms | 0 - 29 MB | NPU
121
+ | XLSR | TFLITE | w8a8 | Qualcomm® QCS6490 | 1.181 ms | 0 - 3 MB | NPU
122
+ | XLSR | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 0.914 ms | 0 - 20 MB | NPU
123
+ | XLSR | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 0.385 ms | 0 - 1 MB | NPU
124
+ | XLSR | TFLITE | w8a8 | Qualcomm® SA8775P | 0.597 ms | 0 - 21 MB | NPU
125
+ | XLSR | TFLITE | w8a8 | Qualcomm® QCS9075 | 0.577 ms | 0 - 3 MB | NPU
126
+ | XLSR | TFLITE | w8a8 | Qualcomm® QCM6690 | 1.622 ms | 0 - 18 MB | NPU
127
+ | XLSR | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 0.529 ms | 0 - 30 MB | NPU
128
+ | XLSR | TFLITE | w8a8 | Qualcomm® SA7255P | 0.914 ms | 0 - 20 MB | NPU
129
+ | XLSR | TFLITE | w8a8 | Qualcomm® SA8295P | 0.771 ms | 0 - 17 MB | NPU
130
+ | XLSR | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.212 ms | 0 - 20 MB | NPU
131
+ | XLSR | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.402 ms | 0 - 19 MB | NPU
132
 
133
  ## License
134
  * The license for the original implementation of XLSR can be found