Hugging Face's logo

qualcomm
/
XLSR

Image-to-Image
PyTorch
android
Model card Files
xet
 Community
1
qaihm-bot commited on
Commit
f539d20
·
verified ·
1 Parent(s): 897057b

v0.64.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.

Files changed (2) hide show
  1. README.md +36 -38
  2. release_assets.json +7 -7
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/v0.63.0/src/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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-onnx-float.zip)
31
- | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-onnx-w8a8.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-qnn_dlc-w8a8.zip)
34
- | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-tflite-float.zip)
35
- | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/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/v0.63.0/src/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/v0.63.0/src/qai_hub_models/models/xlsr) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -90,40 +90,37 @@ See our repository for [XLSR on GitHub](https://github.com/qualcomm/ai-hub-model
90
  | XLSR | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.565 ms | 0 - 25 MB | NPU
91
  | XLSR | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.255 ms | 0 - 30 MB | NPU
92
  | XLSR | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.565 ms | 0 - 25 MB | NPU
93
- | XLSR | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.337 ms | 0 - 26 MB | NPU
94
- | XLSR | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.361 ms | 0 - 25 MB | NPU
95
- | XLSR | QNN_DLC | float | Snapdragon® X2 Elite | 0.439 ms | 0 - 0 MB | NPU
96
  | XLSR | QNN_DLC | float | Snapdragon® X Elite | 0.889 ms | 0 - 0 MB | NPU
97
  | XLSR | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.466 ms | 0 - 34 MB | NPU
98
- | XLSR | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.16 ms | 0 - 36 MB | NPU
99
  | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 0.938 ms | 0 - 6 MB | NPU
100
- | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.77 ms | 0 - 2 MB | NPU
101
- | XLSR | QNN_DLC | float | Qualcomm® SA8775P | 1.142 ms | 0 - 27 MB | NPU
102
- | XLSR | QNN_DLC | float | Qualcomm® SA8650P | 1.142 ms | 0 - 27 MB | NPU
103
- | XLSR | QNN_DLC | float | Qualcomm® SA8255P | 1.142 ms | 0 - 27 MB | NPU
104
- | XLSR | QNN_DLC | float | Qualcomm® QCS8450 | 1.16 ms | 0 - 36 MB | NPU
105
- | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.016 ms | 0 - 6 MB | NPU
106
  | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.889 ms | 0 - 0 MB | NPU
107
- | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.361 ms | 0 - 25 MB | NPU
108
- | XLSR | QNN_DLC | float | Qualcomm® SA8295P | 1.234 ms | 0 - 22 MB | NPU
109
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.175 ms | 0 - 27 MB | NPU
110
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.216 ms | 0 - 24 MB | NPU
111
- | XLSR | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.248 ms | 0 - 0 MB | NPU
112
- | XLSR | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.473 ms | 0 - 0 MB | NPU
113
  | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.238 ms | 0 - 34 MB | NPU
114
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.459 ms | 0 - 36 MB | NPU
115
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.42 ms | 2 - 5 MB | NPU
116
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.716 ms | 0 - 4 MB | NPU
117
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.41 ms | 0 - 2 MB | NPU
118
- | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.459 ms | 0 - 36 MB | NPU
119
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.5 ms | 2 - 5 MB | NPU
120
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.473 ms | 0 - 0 MB | NPU
121
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.631 ms | 0 - 23 MB | NPU
122
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.407 ms | 0 - 23 MB | NPU
123
- | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.216 ms | 0 - 24 MB | NPU
124
- | XLSR | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.874 ms | 0 - 25 MB | NPU
125
- | XLSR | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.647 ms | 0 - 23 MB | NPU
126
- | XLSR | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.407 ms | 0 - 23 MB | NPU
127
  | XLSR | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.802 ms | 0 - 27 MB | NPU
128
  | XLSR | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.974 ms | 0 - 25 MB | NPU
129
  | XLSR | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.408 ms | 0 - 34 MB | NPU
@@ -153,6 +150,7 @@ See our repository for [XLSR on GitHub](https://github.com/qualcomm/ai-hub-model
153
  | XLSR | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.589 ms | 0 - 23 MB | NPU
154
  | XLSR | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.416 ms | 0 - 24 MB | NPU
155
  | XLSR | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.222 ms | 0 - 24 MB | NPU
 
156
  | XLSR | TFLITE | w8a8 | Qualcomm® SA8295P | 0.684 ms | 0 - 23 MB | NPU
157
  | XLSR | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.416 ms | 0 - 24 MB | NPU
158
 
 
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/v0.64.0/src/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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-onnx-float.zip)
31
+ | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-onnx-w8a8.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-qnn_dlc-w8a8.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-tflite-float.zip)
35
+ | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/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/v0.64.0/src/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/v0.64.0/src/qai_hub_models/models/xlsr) for usage instructions.
50
 
51
  ## Model Details
52
 
 
90
  | XLSR | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.565 ms | 0 - 25 MB | NPU
91
  | XLSR | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.255 ms | 0 - 30 MB | NPU
92
  | XLSR | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.565 ms | 0 - 25 MB | NPU
93
+ | XLSR | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.34 ms | 0 - 27 MB | NPU
94
+ | XLSR | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.361 ms | 0 - 29 MB | NPU
95
+ | XLSR | QNN_DLC | float | Snapdragon® X2 Elite | 0.397 ms | 0 - 0 MB | NPU
96
  | XLSR | QNN_DLC | float | Snapdragon® X Elite | 0.889 ms | 0 - 0 MB | NPU
97
  | XLSR | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.466 ms | 0 - 34 MB | NPU
98
+ | XLSR | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.1 ms | 0 - 35 MB | NPU
99
  | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 0.938 ms | 0 - 6 MB | NPU
100
+ | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.788 ms | 0 - 1 MB | NPU
101
+ | XLSR | QNN_DLC | float | Qualcomm® QCS8450 | 1.1 ms | 0 - 35 MB | NPU
102
+ | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.02 ms | 0 - 6 MB | NPU
 
 
 
103
  | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.889 ms | 0 - 0 MB | NPU
104
+ | XLSR | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.361 ms | 0 - 29 MB | NPU
105
+ | XLSR | QNN_DLC | float | Qualcomm® SA8295P | 1.23 ms | 0 - 22 MB | NPU
106
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.173 ms | 0 - 28 MB | NPU
107
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.213 ms | 0 - 28 MB | NPU
108
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.26 ms | 0 - 0 MB | NPU
109
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.486 ms | 0 - 0 MB | NPU
110
  | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.238 ms | 0 - 34 MB | NPU
111
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.454 ms | 0 - 35 MB | NPU
112
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.423 ms | 0 - 3 MB | NPU
113
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.413 ms | 0 - 4 MB | NPU
114
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.37 ms | 0 - 2 MB | NPU
115
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.454 ms | 0 - 35 MB | NPU
116
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.499 ms | 0 - 3 MB | NPU
117
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.486 ms | 0 - 0 MB | NPU
118
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.625 ms | 0 - 23 MB | NPU
119
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.404 ms | 0 - 23 MB | NPU
120
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.213 ms | 0 - 28 MB | NPU
121
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® SA7255P | 0.885 ms | 0 - 26 MB | NPU
122
+ | XLSR | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.655 ms | 0 - 23 MB | NPU
123
+ | XLSR | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.404 ms | 0 - 23 MB | NPU
124
  | XLSR | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.802 ms | 0 - 27 MB | NPU
125
  | XLSR | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.974 ms | 0 - 25 MB | NPU
126
  | XLSR | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.408 ms | 0 - 34 MB | NPU
 
150
  | XLSR | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.589 ms | 0 - 23 MB | NPU
151
  | XLSR | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.416 ms | 0 - 24 MB | NPU
152
  | XLSR | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.222 ms | 0 - 24 MB | NPU
153
+ | XLSR | TFLITE | w8a8 | Qualcomm® SA7255P | 0.931 ms | 0 - 26 MB | NPU
154
  | XLSR | TFLITE | w8a8 | Qualcomm® SA8295P | 0.684 ms | 0 - 23 MB | NPU
155
  | XLSR | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.416 ms | 0 - 24 MB | NPU
156
 
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
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/xlsr/releases/v0.63.0/xlsr-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/xlsr/releases/v0.63.0/xlsr-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/xlsr/releases/v0.63.0/xlsr-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,19 +31,19 @@
31
  "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.50.0.260828221209"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-qnn_dlc-w8a8.zip"
41
  },
42
  "tflite": {
43
  "tool_versions": {
44
  "qairt": "2.50.0.260828221209"
45
  },
46
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.63.0/xlsr-tflite-w8a8.zip"
47
  }
48
  }
49
  }
 
1
  {
2
+ "version": "0.64.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
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/xlsr/releases/v0.64.0/xlsr-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/xlsr/releases/v0.64.0/xlsr-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/xlsr/releases/v0.64.0/xlsr-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.50.0.260828221209",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-onnx-w8a8.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.50.0.260828221209"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-qnn_dlc-w8a8.zip"
41
  },
42
  "tflite": {
43
  "tool_versions": {
44
  "qairt": "2.50.0.260828221209"
45
  },
46
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/xlsr/releases/v0.64.0/xlsr-tflite-w8a8.zip"
47
  }
48
  }
49
  }