Hugging Face's logo

qualcomm
/
Whisper-Small

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
e6b8f6d
·
verified ·
1 Parent(s): 0178924

v0.51.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.51.0 for changelog.

Files changed (2) hide show
  1. README.md +56 -56
  2. release_assets.json +146 -1
README.md CHANGED
@@ -28,24 +28,24 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | PRECOMPILED_QNN_ONNX | float | qualcomm_qcs8550_proxy | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
32
- | PRECOMPILED_QNN_ONNX | float | qualcomm_qcs9075 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
33
- | PRECOMPILED_QNN_ONNX | float | qualcomm_snapdragon_8_elite_for_galaxy | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
34
- | PRECOMPILED_QNN_ONNX | float | qualcomm_snapdragon_8_elite_gen5 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip)
35
- | PRECOMPILED_QNN_ONNX | float | qualcomm_snapdragon_8gen3 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
36
- | PRECOMPILED_QNN_ONNX | float | qualcomm_snapdragon_x2_elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
37
- | PRECOMPILED_QNN_ONNX | float | qualcomm_snapdragon_x_elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
38
- | QNN_CONTEXT_BINARY | float | qualcomm_qcs8450_proxy | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip)
39
- | QNN_CONTEXT_BINARY | float | qualcomm_qcs8550_proxy | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
40
- | QNN_CONTEXT_BINARY | float | qualcomm_qcs9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip)
41
- | QNN_CONTEXT_BINARY | float | qualcomm_sa7255p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip)
42
- | QNN_CONTEXT_BINARY | float | qualcomm_sa8295p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip)
43
- | QNN_CONTEXT_BINARY | float | qualcomm_sa8775p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip)
44
- | QNN_CONTEXT_BINARY | float | qualcomm_snapdragon_8_elite_for_galaxy | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
45
- | QNN_CONTEXT_BINARY | float | qualcomm_snapdragon_8_elite_gen5 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip)
46
- | QNN_CONTEXT_BINARY | float | qualcomm_snapdragon_8gen3 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
47
- | QNN_CONTEXT_BINARY | float | qualcomm_snapdragon_x2_elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
48
- | QNN_CONTEXT_BINARY | float | qualcomm_snapdragon_x_elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
49
 
50
  For more device-specific assets and performance metrics, visit **[Whisper-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small)**.
51
 
@@ -77,44 +77,44 @@ See our repository for [Whisper-Small on GitHub](https://github.com/qualcomm/ai-
77
  ## Performance Summary
78
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
79
  |---|---|---|---|---|---|---
80
- | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.222 ms | 75 - 84 MB | NPU
81
- | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 6.095 ms | 286 - 286 MB | NPU
82
- | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 10.441 ms | 285 - 285 MB | NPU
83
- | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.84 ms | 73 - 85 MB | NPU
84
- | decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 12.133 ms | 61 - 64 MB | NPU
85
- | decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 13.335 ms | 60 - 122 MB | NPU
86
- | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.401 ms | 58 - 68 MB | NPU
87
- | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.266 ms | 60 - 70 MB | NPU
88
- | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 6.525 ms | 60 - 60 MB | NPU
89
- | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 9.745 ms | 60 - 60 MB | NPU
90
- | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 9.819 ms | 37 - 45 MB | NPU
91
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 19.804 ms | 31 - 40 MB | NPU
92
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 12.176 ms | 55 - 65 MB | NPU
93
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 13.725 ms | 60 - 69 MB | NPU
94
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 13.427 ms | 60 - 128 MB | NPU
95
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 17.396 ms | 39 - 49 MB | NPU
96
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 19.804 ms | 31 - 40 MB | NPU
97
- | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 15.117 ms | 46 - 51 MB | NPU
98
- | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.3 ms | 8 - 22 MB | NPU
99
- | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 46.51 ms | 89 - 99 MB | NPU
100
- | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 47.572 ms | 202 - 202 MB | NPU
101
- | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 115.428 ms | 201 - 201 MB | NPU
102
- | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 82.255 ms | 129 - 138 MB | NPU
103
- | encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 112.855 ms | 0 - 225 MB | NPU
104
- | encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 137.101 ms | 126 - 130 MB | NPU
105
- | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 59.055 ms | 127 - 139 MB | NPU
106
- | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 45.088 ms | 1 - 11 MB | NPU
107
- | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 47.766 ms | 0 - 0 MB | NPU
108
- | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 114.908 ms | 0 - 0 MB | NPU
109
- | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 85.441 ms | 1 - 8 MB | NPU
110
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 405.533 ms | 0 - 8 MB | NPU
111
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 112.557 ms | 0 - 3 MB | NPU
112
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 136.563 ms | 0 - 9 MB | NPU
113
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 136.464 ms | 0 - 55 MB | NPU
114
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 281.823 ms | 1 - 10 MB | NPU
115
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 405.533 ms | 0 - 8 MB | NPU
116
- | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 205.937 ms | 1 - 6 MB | NPU
117
- | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 60.399 ms | 1 - 14 MB | NPU
118
 
119
  ## License
120
  * The license for the original implementation of Whisper-Small can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip)
32
+ | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
33
+ | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
34
+ | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
35
+ | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
36
+ | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
37
+ | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
38
+ | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip)
39
+ | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
40
+ | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
41
+ | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
42
+ | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
43
+ | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip)
44
+ | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
45
+ | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip)
46
+ | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip)
47
+ | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip)
48
+ | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip)
49
 
50
  For more device-specific assets and performance metrics, visit **[Whisper-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small)**.
51
 
 
77
  ## Performance Summary
78
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
79
  |---|---|---|---|---|---|---
80
+ | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.239 ms | 75 - 85 MB | NPU
81
+ | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 6.06 ms | 286 - 286 MB | NPU
82
+ | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 10.901 ms | 285 - 285 MB | NPU
83
+ | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.89 ms | 74 - 85 MB | NPU
84
+ | decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 12.214 ms | 61 - 64 MB | NPU
85
+ | decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 13.272 ms | 60 - 122 MB | NPU
86
+ | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.355 ms | 60 - 67 MB | NPU
87
+ | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.347 ms | 60 - 70 MB | NPU
88
+ | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 6.976 ms | 60 - 60 MB | NPU
89
+ | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 9.93 ms | 60 - 60 MB | NPU
90
+ | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 9.815 ms | 60 - 67 MB | NPU
91
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 18.948 ms | 49 - 56 MB | NPU
92
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 12.065 ms | 32 - 40 MB | NPU
93
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 13.703 ms | 55 - 64 MB | NPU
94
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 13.462 ms | 60 - 128 MB | NPU
95
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 17.306 ms | 60 - 69 MB | NPU
96
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 18.948 ms | 49 - 56 MB | NPU
97
+ | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 14.39 ms | 48 - 53 MB | NPU
98
+ | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.354 ms | 0 - 9 MB | NPU
99
+ | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 46.165 ms | 87 - 97 MB | NPU
100
+ | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 47.655 ms | 202 - 202 MB | NPU
101
+ | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 115.731 ms | 201 - 201 MB | NPU
102
+ | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 81.878 ms | 106 - 113 MB | NPU
103
+ | encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 113.115 ms | 0 - 225 MB | NPU
104
+ | encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 137.194 ms | 128 - 132 MB | NPU
105
+ | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 59.021 ms | 129 - 136 MB | NPU
106
+ | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.968 ms | 1 - 10 MB | NPU
107
+ | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 60.085 ms | 0 - 0 MB | NPU
108
+ | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 131.993 ms | 0 - 0 MB | NPU
109
+ | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 97.234 ms | 3 - 10 MB | NPU
110
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 449.524 ms | 0 - 8 MB | NPU
111
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 129.575 ms | 0 - 3 MB | NPU
112
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 154.829 ms | 1 - 10 MB | NPU
113
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 154.882 ms | 2 - 57 MB | NPU
114
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 272.973 ms | 1 - 9 MB | NPU
115
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 449.524 ms | 0 - 8 MB | NPU
116
+ | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 200.107 ms | 1 - 6 MB | NPU
117
+ | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 70.369 ms | 1 - 13 MB | NPU
118
 
119
  ## License
120
  * The license for the original implementation of Whisper-Small can be found
release_assets.json CHANGED
@@ -1 +1,146 @@
1
- {"version":"0.50.2","precisions":{"float":{"chipset_assets":{"qualcomm_qcs8450_proxy":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip"}},"qualcomm_qcs8550_proxy":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip"}},"qualcomm_qcs9075":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip"}},"qualcomm_sa7255p":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip"}},"qualcomm_sa8295p":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip"}},"qualcomm_sa8775p":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip"}},"qualcomm_snapdragon_8_elite_for_galaxy":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"}},"qualcomm_snapdragon_8_elite_gen5":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip"}},"qualcomm_snapdragon_8gen3":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip"}},"qualcomm_snapdragon_x2_elite":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip"}},"qualcomm_snapdragon_x_elite":{"qnn_context_binary":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip"},"precompiled_qnn_onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.50.2/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip"}}}}}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.51.0",
3
+ "precisions": {
4
+ "float": {
5
+ "chipset_assets": {
6
+ "qualcomm-snapdragon-8gen3": {
7
+ "qnn_context_binary": {
8
+ "tool_versions": {
9
+ "qairt": "2.45.0.260326154327"
10
+ },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip"
12
+ },
13
+ "precompiled_qnn_onnx": {
14
+ "tool_versions": {
15
+ "qairt": "2.42.0.251225135753_193295",
16
+ "onnx_runtime": "1.24.3"
17
+ },
18
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip"
19
+ }
20
+ },
21
+ "qualcomm-snapdragon-8-elite-for-galaxy": {
22
+ "qnn_context_binary": {
23
+ "tool_versions": {
24
+ "qairt": "2.45.0.260326154327"
25
+ },
26
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
27
+ },
28
+ "precompiled_qnn_onnx": {
29
+ "tool_versions": {
30
+ "qairt": "2.42.0.251225135753_193295",
31
+ "onnx_runtime": "1.24.3"
32
+ },
33
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
34
+ }
35
+ },
36
+ "qualcomm-snapdragon-8-elite-gen5": {
37
+ "qnn_context_binary": {
38
+ "tool_versions": {
39
+ "qairt": "2.45.0.260326154327"
40
+ },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip"
42
+ },
43
+ "precompiled_qnn_onnx": {
44
+ "tool_versions": {
45
+ "qairt": "2.42.0.251225135753_193295",
46
+ "onnx_runtime": "1.24.3"
47
+ },
48
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip"
49
+ }
50
+ },
51
+ "qualcomm-snapdragon-x-elite": {
52
+ "qnn_context_binary": {
53
+ "tool_versions": {
54
+ "qairt": "2.45.0.260326154327"
55
+ },
56
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip"
57
+ },
58
+ "precompiled_qnn_onnx": {
59
+ "tool_versions": {
60
+ "qairt": "2.42.0.251225135753_193295",
61
+ "onnx_runtime": "1.24.3"
62
+ },
63
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip"
64
+ }
65
+ },
66
+ "qualcomm-snapdragon-x2-elite": {
67
+ "qnn_context_binary": {
68
+ "tool_versions": {
69
+ "qairt": "2.45.0.260326154327"
70
+ },
71
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip"
72
+ },
73
+ "precompiled_qnn_onnx": {
74
+ "tool_versions": {
75
+ "qairt": "2.42.0.251225135753_193295",
76
+ "onnx_runtime": "1.24.3"
77
+ },
78
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip"
79
+ }
80
+ },
81
+ "qualcomm-sa7255p": {
82
+ "qnn_context_binary": {
83
+ "tool_versions": {
84
+ "qairt": "2.45.0.260326154327"
85
+ },
86
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip"
87
+ }
88
+ },
89
+ "qualcomm-sa8295p": {
90
+ "qnn_context_binary": {
91
+ "tool_versions": {
92
+ "qairt": "2.45.0.260326154327"
93
+ },
94
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip"
95
+ }
96
+ },
97
+ "qualcomm-sa8775p": {
98
+ "qnn_context_binary": {
99
+ "tool_versions": {
100
+ "qairt": "2.45.0.260326154327"
101
+ },
102
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip"
103
+ }
104
+ },
105
+ "qualcomm-qcs8550-proxy": {
106
+ "qnn_context_binary": {
107
+ "tool_versions": {
108
+ "qairt": "2.45.0.260326154327"
109
+ },
110
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip"
111
+ },
112
+ "precompiled_qnn_onnx": {
113
+ "tool_versions": {
114
+ "qairt": "2.42.0.251225135753_193295",
115
+ "onnx_runtime": "1.24.3"
116
+ },
117
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip"
118
+ }
119
+ },
120
+ "qualcomm-qcs9075": {
121
+ "qnn_context_binary": {
122
+ "tool_versions": {
123
+ "qairt": "2.45.0.260326154327"
124
+ },
125
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip"
126
+ },
127
+ "precompiled_qnn_onnx": {
128
+ "tool_versions": {
129
+ "qairt": "2.42.0.251225135753_193295",
130
+ "onnx_runtime": "1.24.3"
131
+ },
132
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip"
133
+ }
134
+ },
135
+ "qualcomm-qcs8450-proxy": {
136
+ "qnn_context_binary": {
137
+ "tool_versions": {
138
+ "qairt": "2.45.0.260326154327"
139
+ },
140
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.51.0/whisper_small-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip"
141
+ }
142
+ }
143
+ }
144
+ }
145
+ }
146
+ }