Hugging Face's logo

qualcomm
/
Distil-Whisper

Automatic Speech Recognition
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
94ed98f
·
verified ·
1 Parent(s): a5c7435

v0.61.0

Browse files

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

Files changed (2) hide show
  1. README.md +95 -95
  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: automatic-speech-recognition
@@ -14,7 +14,7 @@ pipeline_tag: automatic-speech-recognition
14
  Distil-Whisper Small English is a distilled version of Whisper Small, optimized for fast and efficient automatic speech recognition.
15
 
16
  This is based on the implementation of Distil-Whisper found [here](https://github.com/huggingface/distil-whisper).
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/distil_whisper) 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/distil_whisper/releases/v0.60.0/distil_whisper-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/distil_whisper/releases/v0.60.0/distil_whisper-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.60.0/distil_whisper-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[Distil-Whisper on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/distil_whisper)**.
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/distil_whisper) 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 [Distil-Whisper on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/distil_whisper) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -61,96 +61,96 @@ See our repository for [Distil-Whisper on GitHub](https://github.com/qualcomm/ai
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | decoder | ONNX | float | Snapdragon® X2 Elite | 5.314 ms | 40 - 40 MB | NPU
65
- | decoder | ONNX | float | Snapdragon® X Elite | 10.878 ms | 179 - 179 MB | NPU
66
- | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.855 ms | 2 - 490 MB | NPU
67
- | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 18.198 ms | 50 - 399 MB | NPU
68
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 13.121 ms | 40 - 83 MB | NPU
69
- | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.779 ms | 41 - 44 MB | NPU
70
- | decoder | ONNX | float | Qualcomm® QCS8450 | 18.198 ms | 50 - 399 MB | NPU
71
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 13.904 ms | 40 - 82 MB | NPU
72
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.878 ms | 179 - 179 MB | NPU
73
- | decoder | ONNX | float | Qualcomm® Dragonwing�� Q-8750 | 7.264 ms | 0 - 554 MB | NPU
74
- | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 7.264 ms | 0 - 554 MB | NPU
75
- | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.729 ms | 9 - 552 MB | NPU
76
- | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 6.032 ms | 40 - 40 MB | NPU
77
- | decoder | QNN_DLC | float | Snapdragon® X Elite | 10.811 ms | 40 - 40 MB | NPU
78
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.543 ms | 0 - 602 MB | NPU
79
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 18.159 ms | 36 - 338 MB | NPU
80
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.791 ms | 40 - 87 MB | NPU
81
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 19.233 ms | 28 - 526 MB | NPU
82
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.4 ms | 40 - 42 MB | NPU
83
- | decoder | QNN_DLC | float | Qualcomm® SA8775P | 12.852 ms | 29 - 522 MB | NPU
84
- | decoder | QNN_DLC | float | Qualcomm® SA8650P | 12.852 ms | 29 - 522 MB | NPU
85
- | decoder | QNN_DLC | float | Qualcomm® SA8255P | 12.852 ms | 29 - 522 MB | NPU
86
- | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 18.159 ms | 36 - 338 MB | NPU
87
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 12.682 ms | 40 - 86 MB | NPU
88
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.811 ms | 40 - 40 MB | NPU
89
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.317 ms | 0 - 543 MB | NPU
90
- | decoder | QNN_DLC | float | Qualcomm® SA7255P | 19.233 ms | 28 - 526 MB | NPU
91
- | decoder | QNN_DLC | float | Qualcomm® SA8295P | 14.034 ms | 15 - 257 MB | NPU
92
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 7.317 ms | 0 - 543 MB | NPU
93
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.919 ms | 1 - 503 MB | NPU
94
- | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.576 ms | 0 - 744 MB | NPU
95
- | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 18.551 ms | 5 - 467 MB | NPU
96
  | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.899 ms | 0 - 266 MB | NPU
97
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 19.188 ms | 5 - 537 MB | NPU
98
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.534 ms | 5 - 8 MB | NPU
99
- | decoder | TFLITE | float | Qualcomm® SA8775P | 13.032 ms | 4 - 537 MB | NPU
100
- | decoder | TFLITE | float | Qualcomm® SA8650P | 13.032 ms | 4 - 537 MB | NPU
101
- | decoder | TFLITE | float | Qualcomm® SA8255P | 13.032 ms | 4 - 537 MB | NPU
102
- | decoder | TFLITE | float | Qualcomm® QCS8450 | 18.551 ms | 5 - 467 MB | NPU
103
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.793 ms | 0 - 265 MB | NPU
104
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.219 ms | 4 - 573 MB | NPU
105
- | decoder | TFLITE | float | Qualcomm® SA7255P | 19.188 ms | 5 - 537 MB | NPU
106
- | decoder | TFLITE | float | Qualcomm® SA8295P | 13.888 ms | 5 - 297 MB | NPU
107
- | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 7.219 ms | 4 - 573 MB | NPU
108
- | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.833 ms | 4 - 575 MB | NPU
109
- | encoder | ONNX | float | Snapdragon® X2 Elite | 60.315 ms | 133 - 133 MB | NPU
110
- | encoder | ONNX | float | Snapdragon® X Elite | 133.587 ms | 237 - 237 MB | NPU
111
- | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 96.714 ms | 80 - 1162 MB | NPU
112
- | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 270.253 ms | 75 - 1019 MB | NPU
113
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 161.953 ms | 74 - 79 MB | NPU
114
- | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 130.107 ms | 75 - 79 MB | NPU
115
- | encoder | ONNX | float | Qualcomm® QCS8450 | 270.253 ms | 75 - 1019 MB | NPU
116
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 152.725 ms | 80 - 84 MB | NPU
117
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 133.587 ms | 237 - 237 MB | NPU
118
- | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 71.666 ms | 54 - 763 MB | NPU
119
- | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 71.666 ms | 54 - 763 MB | NPU
120
- | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.286 ms | 44 - 778 MB | NPU
121
- | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 59.979 ms | 1 - 1 MB | NPU
122
- | encoder | QNN_DLC | float | Snapdragon® X Elite | 139.271 ms | 1 - 1 MB | NPU
123
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 96.901 ms | 0 - 964 MB | NPU
124
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 269.693 ms | 0 - 822 MB | NPU
125
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 161.93 ms | 1 - 39 MB | NPU
126
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 437.523 ms | 1 - 696 MB | NPU
127
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 135.945 ms | 1 - 4 MB | NPU
128
- | encoder | QNN_DLC | float | Qualcomm® SA8775P | 153.525 ms | 1 - 686 MB | NPU
129
- | encoder | QNN_DLC | float | Qualcomm® SA8650P | 153.525 ms | 1 - 686 MB | NPU
130
- | encoder | QNN_DLC | float | Qualcomm® SA8255P | 153.525 ms | 1 - 686 MB | NPU
131
- | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 269.693 ms | 0 - 822 MB | NPU
132
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 153.348 ms | 1 - 39 MB | NPU
133
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 139.271 ms | 1 - 1 MB | NPU
134
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 71.488 ms | 1 - 691 MB | NPU
135
- | encoder | QNN_DLC | float | Qualcomm® SA7255P | 437.523 ms | 1 - 696 MB | NPU
136
- | encoder | QNN_DLC | float | Qualcomm® SA8295P | 192.847 ms | 1 - 611 MB | NPU
137
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 71.488 ms | 1 - 691 MB | NPU
138
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.934 ms | 0 - 717 MB | NPU
139
- | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 479.653 ms | 42 - 188 MB | GPU
140
- | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 843.366 ms | 41 - 195 MB | GPU
141
  | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2998.255 ms | 0 - 39 MB | GPU
142
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3121.152 ms | 21 - 66 MB | GPU
143
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 653.232 ms | 0 - 303 MB | GPU
144
- | encoder | TFLITE | float | Qualcomm® SA8775P | 1323.818 ms | 29 - 73 MB | GPU
145
- | encoder | TFLITE | float | Qualcomm® SA8650P | 1323.818 ms | 29 - 73 MB | GPU
146
- | encoder | TFLITE | float | Qualcomm® SA8255P | 1323.818 ms | 29 - 73 MB | GPU
147
- | encoder | TFLITE | float | Qualcomm® QCS8450 | 843.366 ms | 41 - 195 MB | GPU
148
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1303.549 ms | 0 - 39 MB | GPU
149
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 410.601 ms | 41 - 79 MB | GPU
150
- | encoder | TFLITE | float | Qualcomm® SA7255P | 3121.152 ms | 21 - 66 MB | GPU
151
- | encoder | TFLITE | float | Qualcomm® SA8295P | 665.962 ms | 38 - 81 MB | GPU
152
- | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 410.601 ms | 41 - 79 MB | GPU
153
- | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 367.452 ms | 24 - 62 MB | GPU
154
 
155
  ## License
156
  * The license for the original implementation of Distil-Whisper can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: mit
4
  tags:
5
  - android
6
  pipeline_tag: automatic-speech-recognition
 
14
  Distil-Whisper Small English is a distilled version of Whisper Small, optimized for fast and efficient automatic speech recognition.
15
 
16
  This is based on the implementation of Distil-Whisper found [here](https://github.com/huggingface/distil-whisper).
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/distil_whisper) 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/distil_whisper/releases/v0.61.0/distil_whisper-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/distil_whisper/releases/v0.61.0/distil_whisper-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.61.0/distil_whisper-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[Distil-Whisper on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/distil_whisper)**.
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/distil_whisper) 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 [Distil-Whisper on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/distil_whisper) for usage instructions.
47
 
48
  ## Model Details
49
 
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
+ | decoder | ONNX | float | Snapdragon® X2 Elite | 5.245 ms | 40 - 40 MB | NPU
65
+ | decoder | ONNX | float | Snapdragon® X Elite | 11.182 ms | 179 - 179 MB | NPU
66
+ | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.846 ms | 0 - 489 MB | NPU
67
+ | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 18.335 ms | 50 - 398 MB | NPU
68
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 13.271 ms | 40 - 83 MB | NPU
69
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.87 ms | 40 - 43 MB | NPU
70
+ | decoder | ONNX | float | Qualcomm® QCS8450 | 18.335 ms | 50 - 398 MB | NPU
71
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 15.634 ms | 40 - 82 MB | NPU
72
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.182 ms | 179 - 179 MB | NPU
73
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 7.24 ms | 0 - 554 MB | NPU
74
+ | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 7.24 ms | 0 - 554 MB | NPU
75
+ | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.748 ms | 6 - 550 MB | NPU
76
+ | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.94 ms | 40 - 40 MB | NPU
77
+ | decoder | QNN_DLC | float | Snapdragon® X Elite | 10.986 ms | 40 - 40 MB | NPU
78
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.61 ms | 0 - 602 MB | NPU
79
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 18.219 ms | 36 - 339 MB | NPU
80
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.82 ms | 40 - 87 MB | NPU
81
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 19.115 ms | 40 - 537 MB | NPU
82
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.469 ms | 40 - 44 MB | NPU
83
+ | decoder | QNN_DLC | float | Qualcomm® SA8775P | 12.96 ms | 30 - 522 MB | NPU
84
+ | decoder | QNN_DLC | float | Qualcomm® SA8650P | 12.96 ms | 30 - 522 MB | NPU
85
+ | decoder | QNN_DLC | float | Qualcomm® SA8255P | 12.96 ms | 30 - 522 MB | NPU
86
+ | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 18.219 ms | 36 - 339 MB | NPU
87
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 12.684 ms | 40 - 86 MB | NPU
88
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.986 ms | 40 - 40 MB | NPU
89
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.307 ms | 4 - 548 MB | NPU
90
+ | decoder | QNN_DLC | float | Qualcomm® SA7255P | 19.115 ms | 40 - 537 MB | NPU
91
+ | decoder | QNN_DLC | float | Qualcomm® SA8295P | 14.02 ms | 20 - 262 MB | NPU
92
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 7.307 ms | 4 - 548 MB | NPU
93
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.925 ms | 1 - 503 MB | NPU
94
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.591 ms | 3 - 746 MB | NPU
95
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 18.323 ms | 5 - 467 MB | NPU
96
  | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.899 ms | 0 - 266 MB | NPU
97
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 19.236 ms | 4 - 537 MB | NPU
98
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.605 ms | 5 - 8 MB | NPU
99
+ | decoder | TFLITE | float | Qualcomm® SA8775P | 12.992 ms | 5 - 538 MB | NPU
100
+ | decoder | TFLITE | float | Qualcomm® SA8650P | 12.992 ms | 5 - 538 MB | NPU
101
+ | decoder | TFLITE | float | Qualcomm® SA8255P | 12.992 ms | 5 - 538 MB | NPU
102
+ | decoder | TFLITE | float | Qualcomm® QCS8450 | 18.323 ms | 5 - 467 MB | NPU
103
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.811 ms | 0 - 265 MB | NPU
104
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.24 ms | 5 - 575 MB | NPU
105
+ | decoder | TFLITE | float | Qualcomm® SA7255P | 19.236 ms | 4 - 537 MB | NPU
106
+ | decoder | TFLITE | float | Qualcomm® SA8295P | 13.902 ms | 5 - 296 MB | NPU
107
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 7.24 ms | 5 - 575 MB | NPU
108
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.842 ms | 4 - 574 MB | NPU
109
+ | encoder | ONNX | float | Snapdragon® X2 Elite | 60.4 ms | 133 - 133 MB | NPU
110
+ | encoder | ONNX | float | Snapdragon® X Elite | 133.596 ms | 237 - 237 MB | NPU
111
+ | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 97.178 ms | 0 - 1079 MB | NPU
112
+ | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 270.258 ms | 76 - 1019 MB | NPU
113
+ | encoder | ONNX | float | Qualcomm�� Dragonwing™ IQ-8275 | 162.463 ms | 74 - 79 MB | NPU
114
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 129.246 ms | 0 - 258 MB | NPU
115
+ | encoder | ONNX | float | Qualcomm® QCS8450 | 270.258 ms | 76 - 1019 MB | NPU
116
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 152.735 ms | 76 - 79 MB | NPU
117
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 133.596 ms | 237 - 237 MB | NPU
118
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 71.573 ms | 79 - 789 MB | NPU
119
+ | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 71.573 ms | 79 - 789 MB | NPU
120
+ | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.128 ms | 68 - 803 MB | NPU
121
+ | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 60.245 ms | 1 - 1 MB | NPU
122
+ | encoder | QNN_DLC | float | Snapdragon® X Elite | 139.945 ms | 1 - 1 MB | NPU
123
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 97.319 ms | 1 - 966 MB | NPU
124
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 270.339 ms | 0 - 822 MB | NPU
125
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 161.731 ms | 1 - 39 MB | NPU
126
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 438.051 ms | 1 - 697 MB | NPU
127
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 135.911 ms | 0 - 6 MB | NPU
128
+ | encoder | QNN_DLC | float | Qualcomm® SA8775P | 153.263 ms | 1 - 686 MB | NPU
129
+ | encoder | QNN_DLC | float | Qualcomm® SA8650P | 153.263 ms | 1 - 686 MB | NPU
130
+ | encoder | QNN_DLC | float | Qualcomm® SA8255P | 153.263 ms | 1 - 686 MB | NPU
131
+ | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 270.339 ms | 0 - 822 MB | NPU
132
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 153.492 ms | 3 - 41 MB | NPU
133
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 139.945 ms | 1 - 1 MB | NPU
134
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 71.457 ms | 1 - 691 MB | NPU
135
+ | encoder | QNN_DLC | float | Qualcomm® SA7255P | 438.051 ms | 1 - 697 MB | NPU
136
+ | encoder | QNN_DLC | float | Qualcomm® SA8295P | 192.968 ms | 1 - 610 MB | NPU
137
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 71.457 ms | 1 - 691 MB | NPU
138
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.819 ms | 0 - 718 MB | NPU
139
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 481.599 ms | 42 - 187 MB | GPU
140
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 839.03 ms | 41 - 194 MB | GPU
141
  | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 2998.255 ms | 0 - 39 MB | GPU
142
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 3123.092 ms | 18 - 62 MB | GPU
143
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 649.127 ms | 0 - 311 MB | GPU
144
+ | encoder | TFLITE | float | Qualcomm® SA8775P | 1324.913 ms | 17 - 61 MB | GPU
145
+ | encoder | TFLITE | float | Qualcomm® SA8650P | 1324.913 ms | 17 - 61 MB | GPU
146
+ | encoder | TFLITE | float | Qualcomm® SA8255P | 1324.913 ms | 17 - 61 MB | GPU
147
+ | encoder | TFLITE | float | Qualcomm® QCS8450 | 839.03 ms | 41 - 194 MB | GPU
148
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1281.735 ms | 0 - 39 MB | GPU
149
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 405.666 ms | 42 - 81 MB | GPU
150
+ | encoder | TFLITE | float | Qualcomm® SA7255P | 3123.092 ms | 18 - 62 MB | GPU
151
+ | encoder | TFLITE | float | Qualcomm® SA8295P | 667.287 ms | 38 - 83 MB | GPU
152
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 405.666 ms | 42 - 81 MB | GPU
153
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 367.921 ms | 40 - 79 MB | GPU
154
 
155
  ## License
156
  * The license for the original implementation of Distil-Whisper can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,17 +8,17 @@
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/distil_whisper/releases/v0.60.0/distil_whisper-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/distil_whisper/releases/v0.60.0/distil_whisper-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {},
21
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.60.0/distil_whisper-tflite-float.zip"
22
  }
23
  }
24
  }
 
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/distil_whisper/releases/v0.61.0/distil_whisper-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/distil_whisper/releases/v0.61.0/distil_whisper-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {},
21
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.61.0/distil_whisper-tflite-float.zip"
22
  }
23
  }
24
  }