Hugging Face's logo

qualcomm
/
Distil-Whisper

Automatic Speech Recognition
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
6505a90
·
verified ·
1 Parent(s): eb11d41

v0.58.0

Browse files

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

Files changed (2) hide show
  1. README.md +90 -84
  2. release_assets.json +4 -4
README.md CHANGED
@@ -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/v0.57.3/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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.57.3/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/v0.57.3/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/v0.57.3/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/v0.57.3/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/v0.57.3/src/qai_hub_models/models/distil_whisper) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -61,84 +61,90 @@ 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 | 5.295 ms | 172 - 172 MB | NPU
65
- | decoder | ONNX | float | Snapdragon® X Elite | 10.821 ms | 211 - 211 MB | NPU
66
- | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.837 ms | 0 - 475 MB | NPU
67
- | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 18.106 ms | 50 - 384 MB | NPU
68
- | decoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 11.846 ms | 0 - 183 MB | NPU
69
- | decoder | ONNX | float | Qualcomm® QCS8450 | 18.106 ms | 50 - 384 MB | NPU
70
- | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 7.28 ms | 11 - 563 MB | NPU
71
- | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.746 ms | 15 - 551 MB | NPU
72
- | decoder | ONNX | float | Qualcomm® QCS9075 | 17.928 ms | 40 - 85 MB | NPU
73
- | decoder | ONNX | float | Qualcomm® QCS8750 | 7.28 ms | 11 - 563 MB | NPU
74
- | decoder | ONNX | float | Qualcomm® QCS7181 | 10.821 ms | 211 - 211 MB | NPU
75
- | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 5.973 ms | 40 - 40 MB | NPU
76
- | decoder | QNN_DLC | float | Snapdragon® X Elite | 11.522 ms | 40 - 40 MB | NPU
77
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.644 ms | 40 - 644 MB | NPU
78
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 18.094 ms | 1 - 303 MB | NPU
79
- | decoder | QNN_DLC | float | Qualcomm® QCS8275 | 19.063 ms | 29 - 526 MB | NPU
80
- | decoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 11.567 ms | 40 - 42 MB | NPU
81
- | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 18.094 ms | 1 - 303 MB | NPU
82
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 7.32 ms | 0 - 542 MB | NPU
83
- | decoder | QNN_DLC | float | Qualcomm® SA8295P | 14.026 ms | 2 - 244 MB | NPU
84
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.936 ms | 1 - 503 MB | NPU
85
- | decoder | QNN_DLC | float | Qualcomm® SA7255P | 19.063 ms | 29 - 526 MB | NPU
86
- | decoder | QNN_DLC | float | Qualcomm® QCS9075 | 16.568 ms | 40 - 86 MB | NPU
87
- | decoder | QNN_DLC | float | Qualcomm® QCS8750 | 7.32 ms | 0 - 542 MB | NPU
88
- | decoder | QNN_DLC | float | Qualcomm® QCS7181 | 11.522 ms | 40 - 40 MB | NPU
89
- | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.607 ms | 4 - 744 MB | NPU
90
- | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 18.406 ms | 5 - 467 MB | NPU
91
- | decoder | TFLITE | float | Qualcomm® QCS8275 | 19.145 ms | 4 - 537 MB | NPU
92
- | decoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 11.608 ms | 5 - 8 MB | NPU
93
- | decoder | TFLITE | float | Qualcomm® SA8775P | 17.183 ms | 41 - 52 MB | CPU
94
- | decoder | TFLITE | float | Qualcomm® SA8650P | 17.183 ms | 41 - 52 MB | CPU
95
- | decoder | TFLITE | float | Qualcomm® SA8255P | 17.183 ms | 41 - 52 MB | CPU
96
- | decoder | TFLITE | float | Qualcomm® QCS8450 | 18.406 ms | 5 - 467 MB | NPU
97
- | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 7.222 ms | 5 - 573 MB | NPU
98
- | decoder | TFLITE | float | Qualcomm® SA8295P | 13.884 ms | 5 - 297 MB | NPU
99
- | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.839 ms | 4 - 574 MB | NPU
100
- | decoder | TFLITE | float | Qualcomm® SA7255P | 19.145 ms | 4 - 537 MB | NPU
101
- | decoder | TFLITE | float | Qualcomm® QCS9075 | 16.364 ms | 0 - 265 MB | NPU
102
- | decoder | TFLITE | float | Qualcomm® QCS8750 | 7.222 ms | 5 - 573 MB | NPU
103
- | encoder | ONNX | float | Snapdragon® X2 Elite | 60.047 ms | 211 - 211 MB | NPU
104
- | encoder | ONNX | float | Snapdragon® X Elite | 132.661 ms | 236 - 236 MB | NPU
105
- | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 97.408 ms | 127 - 1191 MB | NPU
106
- | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 271.563 ms | 75 - 1001 MB | NPU
107
- | encoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 129.944 ms | 0 - 260 MB | NPU
108
- | encoder | ONNX | float | Qualcomm® QCS8450 | 271.563 ms | 75 - 1001 MB | NPU
109
- | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 71.361 ms | 81 - 784 MB | NPU
110
- | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.981 ms | 53 - 778 MB | NPU
111
- | encoder | ONNX | float | Qualcomm® QCS9075 | 169.233 ms | 78 - 124 MB | NPU
112
- | encoder | ONNX | float | Qualcomm® QCS8750 | 71.361 ms | 81 - 784 MB | NPU
113
- | encoder | ONNX | float | Qualcomm® QCS7181 | 132.661 ms | 236 - 236 MB | NPU
114
- | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 60.536 ms | 1 - 1 MB | NPU
115
- | encoder | QNN_DLC | float | Snapdragon® X Elite | 139.974 ms | 1 - 1 MB | NPU
116
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 96.914 ms | 0 - 964 MB | NPU
117
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 266.25 ms | 1 - 824 MB | NPU
118
- | encoder | QNN_DLC | float | Qualcomm® QCS8275 | 437.854 ms | 1 - 695 MB | NPU
119
- | encoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 135.358 ms | 1 - 898 MB | NPU
120
- | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 266.25 ms | 1 - 824 MB | NPU
121
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 71.483 ms | 1 - 691 MB | NPU
122
- | encoder | QNN_DLC | float | Qualcomm® SA8295P | 193.074 ms | 1 - 611 MB | NPU
123
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.723 ms | 0 - 718 MB | NPU
124
- | encoder | QNN_DLC | float | Qualcomm® SA7255P | 437.854 ms | 1 - 695 MB | NPU
125
- | encoder | QNN_DLC | float | Qualcomm® QCS9075 | 170.907 ms | 1 - 39 MB | NPU
126
- | encoder | QNN_DLC | float | Qualcomm® QCS8750 | 71.483 ms | 1 - 691 MB | NPU
127
- | encoder | QNN_DLC | float | Qualcomm® QCS7181 | 139.974 ms | 1 - 1 MB | NPU
128
- | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 479.703 ms | 0 - 144 MB | GPU
129
- | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 841.152 ms | 41 - 195 MB | GPU
130
- | encoder | TFLITE | float | Qualcomm® QCS8275 | 3109.319 ms | 24 - 69 MB | GPU
131
- | encoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 652.021 ms | 0 - 291 MB | GPU
132
- | encoder | TFLITE | float | Qualcomm® SA8775P | 1310.069 ms | 15 - 59 MB | GPU
133
- | encoder | TFLITE | float | Qualcomm® SA8650P | 1310.069 ms | 15 - 59 MB | GPU
134
- | encoder | TFLITE | float | Qualcomm® SA8255P | 1310.069 ms | 15 - 59 MB | GPU
135
- | encoder | TFLITE | float | Qualcomm® QCS8450 | 841.152 ms | 41 - 195 MB | GPU
136
- | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 403.588 ms | 41 - 81 MB | GPU
137
- | encoder | TFLITE | float | Qualcomm® SA8295P | 667.003 ms | 40 - 84 MB | GPU
138
- | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 370.741 ms | 40 - 79 MB | GPU
139
- | encoder | TFLITE | float | Qualcomm® SA7255P | 3109.319 ms | 24 - 69 MB | GPU
140
- | encoder | TFLITE | float | Qualcomm® QCS9075 | 1264.937 ms | 0 - 40 MB | GPU
141
- | encoder | TFLITE | float | Qualcomm® QCS8750 | 403.588 ms | 41 - 81 MB | GPU
 
 
 
 
 
 
142
 
143
  ## License
144
  * The license for the original implementation of Distil-Whisper can be found
 
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/v0.58.0/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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.58.0/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/v0.58.0/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/v0.58.0/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/v0.58.0/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/v0.58.0/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 | 5.285 ms | 40 - 40 MB | NPU
65
+ | decoder | ONNX | float | Snapdragon® X Elite | 10.717 ms | 179 - 179 MB | NPU
66
+ | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.795 ms | 2 - 489 MB | NPU
67
+ | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 18.22 ms | 50 - 396 MB | NPU
68
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.846 ms | 0 - 183 MB | NPU
69
+ | decoder | ONNX | float | Qualcomm® QCS8450 | 18.22 ms | 50 - 396 MB | NPU
70
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 15.344 ms | 40 - 82 MB | NPU
71
+ | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.737 ms | 2 - 542 MB | NPU
72
+ | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 7.259 ms | 15 - 567 MB | NPU
73
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 7.259 ms | 15 - 567 MB | NPU
74
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.717 ms | 179 - 179 MB | NPU
75
+ | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 6.077 ms | 40 - 40 MB | NPU
76
+ | decoder | QNN_DLC | float | Snapdragon® X Elite | 11.027 ms | 40 - 40 MB | NPU
77
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.627 ms | 39 - 640 MB | NPU
78
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 18.132 ms | 36 - 338 MB | NPU
79
+ | decoder | QNN_DLC | float | Qualcomm® QCS8275 | 19.086 ms | 29 - 526 MB | NPU
80
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.513 ms | 40 - 541 MB | NPU
81
+ | decoder | QNN_DLC | float | Qualcomm® SA8775P | 12.944 ms | 30 - 521 MB | NPU
82
+ | decoder | QNN_DLC | float | Qualcomm® SA8650P | 12.944 ms | 30 - 521 MB | NPU
83
+ | decoder | QNN_DLC | float | Qualcomm® SA8255P | 12.944 ms | 30 - 521 MB | NPU
84
+ | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 18.132 ms | 36 - 338 MB | NPU
85
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 12.65 ms | 42 - 88 MB | NPU
86
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.928 ms | 1 - 502 MB | NPU
87
+ | decoder | QNN_DLC | float | Qualcomm® SA7255P | 19.086 ms | 29 - 526 MB | NPU
88
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 7.306 ms | 0 - 543 MB | NPU
89
+ | decoder | QNN_DLC | float | Qualcomm® SA8295P | 14.042 ms | 18 - 260 MB | NPU
90
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 7.306 ms | 0 - 543 MB | NPU
91
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 11.027 ms | 40 - 40 MB | NPU
92
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.707 ms | 0 - 743 MB | NPU
93
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 18.449 ms | 5 - 466 MB | NPU
94
+ | decoder | TFLITE | float | Qualcomm® QCS8275 | 19.323 ms | 5 - 539 MB | NPU
95
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.475 ms | 5 - 8 MB | NPU
96
+ | decoder | TFLITE | float | Qualcomm® SA8775P | 13.02 ms | 5 - 538 MB | NPU
97
+ | decoder | TFLITE | float | Qualcomm® SA8650P | 13.02 ms | 5 - 538 MB | NPU
98
+ | decoder | TFLITE | float | Qualcomm® SA8255P | 13.02 ms | 5 - 538 MB | NPU
99
+ | decoder | TFLITE | float | Qualcomm® QCS8450 | 18.449 ms | 5 - 466 MB | NPU
100
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 16.364 ms | 0 - 265 MB | NPU
101
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.84 ms | 4 - 575 MB | NPU
102
+ | decoder | TFLITE | float | Qualcomm® SA7255P | 19.323 ms | 5 - 539 MB | NPU
103
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 7.226 ms | 4 - 574 MB | NPU
104
+ | decoder | TFLITE | float | Qualcomm® SA8295P | 13.952 ms | 5 - 297 MB | NPU
105
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 7.226 ms | 4 - 574 MB | NPU
106
+ | encoder | ONNX | float | Snapdragon® X2 Elite | 60.235 ms | 133 - 133 MB | NPU
107
+ | encoder | ONNX | float | Snapdragon® X Elite | 133.488 ms | 237 - 237 MB | NPU
108
+ | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 97.932 ms | 81 - 1156 MB | NPU
109
+ | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 269.405 ms | 72 - 1006 MB | NPU
110
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 129.944 ms | 0 - 260 MB | NPU
111
+ | encoder | ONNX | float | Qualcomm® QCS8450 | 269.405 ms | 72 - 1006 MB | NPU
112
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 153.353 ms | 81 - 84 MB | NPU
113
+ | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.909 ms | 46 - 775 MB | NPU
114
+ | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 71.501 ms | 79 - 785 MB | NPU
115
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 71.501 ms | 79 - 785 MB | NPU
116
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 133.488 ms | 237 - 237 MB | NPU
117
+ | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 60.347 ms | 1 - 1 MB | NPU
118
+ | encoder | QNN_DLC | float | Snapdragon® X Elite | 139.879 ms | 1 - 1 MB | NPU
119
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 97.308 ms | 0 - 964 MB | NPU
120
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 268.383 ms | 0 - 823 MB | NPU
121
+ | encoder | QNN_DLC | float | Qualcomm® QCS8275 | 437.616 ms | 1 - 696 MB | NPU
122
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 135.106 ms | 0 - 548 MB | NPU
123
+ | encoder | QNN_DLC | float | Qualcomm® SA8775P | 154.308 ms | 1 - 687 MB | NPU
124
+ | encoder | QNN_DLC | float | Qualcomm® SA8650P | 154.308 ms | 1 - 687 MB | NPU
125
+ | encoder | QNN_DLC | float | Qualcomm® SA8255P | 154.308 ms | 1 - 687 MB | NPU
126
+ | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 268.383 ms | 0 - 823 MB | NPU
127
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 153.453 ms | 1 - 39 MB | NPU
128
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.432 ms | 0 - 718 MB | NPU
129
+ | encoder | QNN_DLC | float | Qualcomm® SA7255P | 437.616 ms | 1 - 696 MB | NPU
130
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 71.17 ms | 1 - 691 MB | NPU
131
+ | encoder | QNN_DLC | float | Qualcomm® SA8295P | 193.09 ms | 1 - 611 MB | NPU
132
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 71.17 ms | 1 - 691 MB | NPU
133
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 139.879 ms | 1 - 1 MB | NPU
134
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 475.47 ms | 42 - 187 MB | GPU
135
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 836.934 ms | 41 - 194 MB | GPU
136
+ | encoder | TFLITE | float | Qualcomm® QCS8275 | 3113.712 ms | 36 - 81 MB | GPU
137
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 653.403 ms | 0 - 281 MB | GPU
138
+ | encoder | TFLITE | float | Qualcomm® SA8775P | 1324.874 ms | 32 - 75 MB | GPU
139
+ | encoder | TFLITE | float | Qualcomm® SA8650P | 1324.874 ms | 32 - 75 MB | GPU
140
+ | encoder | TFLITE | float | Qualcomm® SA8255P | 1324.874 ms | 32 - 75 MB | GPU
141
+ | encoder | TFLITE | float | Qualcomm® QCS8450 | 836.934 ms | 41 - 194 MB | GPU
142
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1264.937 ms | 0 - 40 MB | GPU
143
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 359.55 ms | 42 - 82 MB | GPU
144
+ | encoder | TFLITE | float | Qualcomm® SA7255P | 3113.712 ms | 36 - 81 MB | GPU
145
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 400.716 ms | 40 - 79 MB | GPU
146
+ | encoder | TFLITE | float | Qualcomm® SA8295P | 672.024 ms | 40 - 84 MB | GPU
147
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 400.716 ms | 40 - 79 MB | GPU
148
 
149
  ## License
150
  * The license for the original implementation of Distil-Whisper can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -7,20 +7,20 @@
7
  "tool_versions": {
8
  "litert": "1.4.4"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.57.3/distil_whisper-tflite-float.zip"
11
  },
12
  "qnn_dlc": {
13
  "tool_versions": {
14
  "qairt": "2.45.0.260326154327"
15
  },
16
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.57.3/distil_whisper-qnn_dlc-float.zip"
17
  },
18
  "onnx": {
19
  "tool_versions": {
20
  "qairt": "2.45.0.260326154327",
21
  "onnx_runtime": "1.25.0"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.57.3/distil_whisper-onnx-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
7
  "tool_versions": {
8
  "litert": "1.4.4"
9
  },
10
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.58.0/distil_whisper-tflite-float.zip"
11
  },
12
  "qnn_dlc": {
13
  "tool_versions": {
14
  "qairt": "2.45.0.260326154327"
15
  },
16
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.58.0/distil_whisper-qnn_dlc-float.zip"
17
  },
18
  "onnx": {
19
  "tool_versions": {
20
  "qairt": "2.45.0.260326154327",
21
  "onnx_runtime": "1.25.0"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/distil_whisper/releases/v0.58.0/distil_whisper-onnx-float.zip"
24
  }
25
  }
26
  }