Hugging Face's logo

qualcomm
/
Whisper-Small-Quantized

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
40e68e8
·
verified ·
1 Parent(s): 7d2d12b

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 +98 -62
  2. release_assets.json +234 -1
README.md CHANGED
@@ -28,26 +28,38 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_qcm6690 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip)
32
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip)
33
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip)
34
- | PRECOMPILED_QNN_ONNX | w8a16 | qualcomm_snapdragon_7gen4 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip)
35
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
36
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
37
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip)
38
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip)
39
- | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip)
40
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_qcm6690 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip)
41
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_qcs8550_proxy | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip)
42
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_qcs9075 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.zip)
43
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_sa7255p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip)
44
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_sa8775p | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip)
45
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_7gen4 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip)
46
- | QNN_CONTEXT_BINARY | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
47
- | QNN_CONTEXT_BINARY | w8a16 | 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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
48
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_8gen3 | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip)
49
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_x2_elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip)
50
- | QNN_CONTEXT_BINARY | w8a16 | qualcomm_snapdragon_x_elite | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip)
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
  For more device-specific assets and performance metrics, visit **[Whisper-Small-Quantized on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small_quantized)**.
53
 
@@ -75,48 +87,72 @@ See our repository for [Whisper-Small-Quantized on GitHub](https://github.com/qu
75
  ## Performance Summary
76
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
77
  |---|---|---|---|---|---|---
78
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.979 ms | 38 - 48 MB | NPU
79
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.812 ms | 185 - 185 MB | NPU
80
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 7.967 ms | 185 - 185 MB | NPU
81
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.354 ms | 40 - 48 MB | NPU
82
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.319 ms | 29 - 32 MB | NPU
83
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 9.06 ms | 24 - 57 MB | NPU
84
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 37.459 ms | 29 - 39 MB | NPU
85
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.757 ms | 25 - 33 MB | NPU
86
- | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.823 ms | 30 - 36 MB | NPU
87
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.963 ms | 30 - 40 MB | NPU
88
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.191 ms | 30 - 30 MB | NPU
89
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.57 ms | 30 - 30 MB | NPU
90
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.254 ms | 30 - 39 MB | NPU
91
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 13.457 ms | 13 - 20 MB | NPU
92
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.158 ms | 30 - 32 MB | NPU
93
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 9.257 ms | 29 - 38 MB | NPU
94
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 8.92 ms | 25 - 60 MB | NPU
95
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 36.842 ms | 30 - 37 MB | NPU
96
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 13.457 ms | 13 - 20 MB | NPU
97
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.751 ms | 22 - 35 MB | NPU
98
- | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.848 ms | 30 - 37 MB | NPU
99
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 175.256 ms | 63 - 73 MB | NPU
100
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 154.028 ms | 127 - 127 MB | NPU
101
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 264.69 ms | 127 - 127 MB | NPU
102
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 244.062 ms | 63 - 75 MB | NPU
103
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 350.116 ms | 55 - 58 MB | NPU
104
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 255.908 ms | 63 - 66 MB | NPU
105
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 4170.586 ms | 2 - 13 MB | NPU
106
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 200.797 ms | 63 - 75 MB | NPU
107
- | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 457.805 ms | 56 - 66 MB | NPU
108
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 175.95 ms | 1 - 11 MB | NPU
109
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 153.643 ms | 0 - 0 MB | NPU
110
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 296.075 ms | 0 - 0 MB | NPU
111
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 269.335 ms | 1 - 8 MB | NPU
112
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 518.268 ms | 1 - 9 MB | NPU
113
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 368.292 ms | 1 - 2 MB | NPU
114
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 312.155 ms | 1 - 10 MB | NPU
115
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 293.695 ms | 0 - 29 MB | NPU
116
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 4234.28 ms | 0 - 7 MB | NPU
117
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 518.268 ms | 1 - 9 MB | NPU
118
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 221.77 ms | 1 - 14 MB | NPU
119
- | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 468.035 ms | 1 - 7 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
120
 
121
  ## License
122
  * The license for the original implementation of Whisper-Small-Quantized can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
32
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip)
33
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip)
34
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip)
35
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip)
36
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
37
+ | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip)
38
+ | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip)
39
+ | PRECOMPILED_QNN_ONNX | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip)
40
+ | QNN_CONTEXT_BINARY | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
41
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip)
42
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip)
43
+ | QNN_CONTEXT_BINARY | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip)
44
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip)
45
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip)
46
+ | QNN_CONTEXT_BINARY | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
47
+ | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip)
48
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip)
49
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip)
50
+ | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.zip)
51
+ | VOICE_AI | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_gen5.zip)
52
+ | VOICE_AI | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_x2_elite.zip)
53
+ | VOICE_AI | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_x_elite.zip)
54
+ | VOICE_AI | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8gen3.zip)
55
+ | VOICE_AI | w8a16 | qualcomm-qcs8275 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8275.zip)
56
+ | VOICE_AI | w8a16 | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8550_proxy.zip)
57
+ | VOICE_AI | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa8775p.zip)
58
+ | VOICE_AI | w8a16 | 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_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip)
59
+ | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_7gen4.zip)
60
+ | VOICE_AI | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa7255p.zip)
61
+ | VOICE_AI | w8a16 | Qualcomm® QCM6690 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcm6690.zip)
62
+ | VOICE_AI | w8a16 | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs9075.zip)
63
 
64
  For more device-specific assets and performance metrics, visit **[Whisper-Small-Quantized on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small_quantized)**.
65
 
 
87
  ## Performance Summary
88
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
89
  |---|---|---|---|---|---|---
90
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.971 ms | 30 - 41 MB | NPU
91
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 3.806 ms | 185 - 185 MB | NPU
92
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 8.145 ms | 185 - 185 MB | NPU
93
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.272 ms | 33 - 40 MB | NPU
94
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.295 ms | 28 - 30 MB | NPU
95
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 9.066 ms | 30 - 62 MB | NPU
96
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 42.773 ms | 28 - 38 MB | NPU
97
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.772 ms | 19 - 32 MB | NPU
98
+ | decoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.887 ms | 29 - 36 MB | NPU
99
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.919 ms | 30 - 40 MB | NPU
100
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 4.218 ms | 30 - 30 MB | NPU
101
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 7.414 ms | 30 - 30 MB | NPU
102
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.967 ms | 24 - 32 MB | NPU
103
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 12.666 ms | 10 - 18 MB | NPU
104
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.816 ms | 31 - 33 MB | NPU
105
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 8.953 ms | 26 - 35 MB | NPU
106
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 8.656 ms | 25 - 60 MB | NPU
107
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 29.637 ms | 30 - 37 MB | NPU
108
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 12.666 ms | 10 - 18 MB | NPU
109
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.62 ms | 22 - 31 MB | NPU
110
+ | decoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.449 ms | 29 - 36 MB | NPU
111
+ | decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.902 ms | 30 - 40 MB | NPU
112
+ | decoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 4.247 ms | 30 - 30 MB | NPU
113
+ | decoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 7.358 ms | 30 - 30 MB | NPU
114
+ | decoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.003 ms | 30 - 39 MB | NPU
115
+ | decoder | VOICE_AI | w8a16 | Qualcomm® QCS8275 (Proxy) | 12.775 ms | 30 - 39 MB | NPU
116
+ | decoder | VOICE_AI | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.793 ms | 30 - 32 MB | NPU
117
+ | decoder | VOICE_AI | w8a16 | Qualcomm® SA8775P | 8.997 ms | 29 - 38 MB | NPU
118
+ | decoder | VOICE_AI | w8a16 | Qualcomm® QCS9075 | 8.655 ms | 25 - 60 MB | NPU
119
+ | decoder | VOICE_AI | w8a16 | Qualcomm® QCM6690 | 30.457 ms | 28 - 34 MB | NPU
120
+ | decoder | VOICE_AI | w8a16 | Qualcomm® SA7255P | 12.775 ms | 30 - 39 MB | NPU
121
+ | decoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.612 ms | 21 - 35 MB | NPU
122
+ | decoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.479 ms | 30 - 37 MB | NPU
123
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 176.433 ms | 63 - 73 MB | NPU
124
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 155.344 ms | 127 - 127 MB | NPU
125
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 266.244 ms | 127 - 127 MB | NPU
126
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 248.059 ms | 63 - 70 MB | NPU
127
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 333.657 ms | 0 - 129 MB | NPU
128
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS9075 | 256.887 ms | 63 - 66 MB | NPU
129
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCM6690 | 4336.016 ms | 2 - 13 MB | NPU
130
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 196.563 ms | 63 - 75 MB | NPU
131
+ | encoder | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 457.053 ms | 57 - 67 MB | NPU
132
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 188.87 ms | 1 - 10 MB | NPU
133
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 156.171 ms | 0 - 0 MB | NPU
134
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 302.188 ms | 0 - 0 MB | NPU
135
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 269.617 ms | 1 - 8 MB | NPU
136
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8275 (Proxy) | 525.284 ms | 0 - 8 MB | NPU
137
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8550 (Proxy) | 392.632 ms | 1 - 33 MB | NPU
138
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 315.833 ms | 1 - 10 MB | NPU
139
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS9075 | 297.123 ms | 0 - 29 MB | NPU
140
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCM6690 | 4189.979 ms | 1 - 12 MB | NPU
141
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 525.284 ms | 0 - 8 MB | NPU
142
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 222.474 ms | 1 - 10 MB | NPU
143
+ | encoder | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 7 Gen 4 Mobile | 482.192 ms | 0 - 7 MB | NPU
144
+ | encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 191.472 ms | 1 - 10 MB | NPU
145
+ | encoder | VOICE_AI | w8a16 | Snapdragon® X2 Elite | 153.678 ms | 0 - 0 MB | NPU
146
+ | encoder | VOICE_AI | w8a16 | Snapdragon® X Elite | 303.085 ms | 0 - 0 MB | NPU
147
+ | encoder | VOICE_AI | w8a16 | Snapdragon® 8 Gen 3 Mobile | 269.398 ms | 1 - 8 MB | NPU
148
+ | encoder | VOICE_AI | w8a16 | Qualcomm® QCS8275 (Proxy) | 512.111 ms | 1 - 9 MB | NPU
149
+ | encoder | VOICE_AI | w8a16 | Qualcomm® QCS8550 (Proxy) | 376.546 ms | 1 - 26 MB | NPU
150
+ | encoder | VOICE_AI | w8a16 | Qualcomm® SA8775P | 316.614 ms | 0 - 9 MB | NPU
151
+ | encoder | VOICE_AI | w8a16 | Qualcomm® QCS9075 | 296.165 ms | 1 - 29 MB | NPU
152
+ | encoder | VOICE_AI | w8a16 | Qualcomm® QCM6690 | 4457.874 ms | 1 - 12 MB | NPU
153
+ | encoder | VOICE_AI | w8a16 | Qualcomm® SA7255P | 512.111 ms | 1 - 9 MB | NPU
154
+ | encoder | VOICE_AI | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 226.069 ms | 1 - 9 MB | NPU
155
+ | encoder | VOICE_AI | w8a16 | Snapdragon® 7 Gen 4 Mobile | 480.523 ms | 1 - 7 MB | NPU
156
 
157
  ## License
158
  * The license for the original implementation of Whisper-Small-Quantized can be found
release_assets.json CHANGED
@@ -1 +1,234 @@
1
- {"version":"0.50.2","precisions":{"w8a16":{"chipset_assets":{"qualcomm_qcm6690":{"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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip"}},"qualcomm_snapdragon_7gen4":{"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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-qnn_context_binary-w8a16-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_quantized/releases/v0.50.2/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip"}}}}}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.51.0",
3
+ "precisions": {
4
+ "w8a16": {
5
+ "chipset_assets": {
6
+ "qualcomm-qcs8275": {
7
+ "voice_ai": {
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_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8275.zip"
12
+ }
13
+ },
14
+ "qualcomm-snapdragon-8gen3": {
15
+ "qnn_context_binary": {
16
+ "tool_versions": {
17
+ "qairt": "2.45.0.260326154327"
18
+ },
19
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8gen3.zip"
20
+ },
21
+ "precompiled_qnn_onnx": {
22
+ "tool_versions": {
23
+ "qairt": "2.42.0.251225135753_193295",
24
+ "onnx_runtime": "1.24.3"
25
+ },
26
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8gen3.zip"
27
+ },
28
+ "voice_ai": {
29
+ "tool_versions": {
30
+ "qairt": "2.45.0.260326154327"
31
+ },
32
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8gen3.zip"
33
+ }
34
+ },
35
+ "qualcomm-snapdragon-8-elite-for-galaxy": {
36
+ "qnn_context_binary": {
37
+ "tool_versions": {
38
+ "qairt": "2.45.0.260326154327"
39
+ },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip"
41
+ },
42
+ "precompiled_qnn_onnx": {
43
+ "tool_versions": {
44
+ "qairt": "2.42.0.251225135753_193295",
45
+ "onnx_runtime": "1.24.3"
46
+ },
47
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip"
48
+ },
49
+ "voice_ai": {
50
+ "tool_versions": {
51
+ "qairt": "2.45.0.260326154327"
52
+ },
53
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_for_galaxy.zip"
54
+ }
55
+ },
56
+ "qualcomm-snapdragon-7gen4": {
57
+ "qnn_context_binary": {
58
+ "tool_versions": {
59
+ "qairt": "2.45.0.260326154327"
60
+ },
61
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_7gen4.zip"
62
+ },
63
+ "precompiled_qnn_onnx": {
64
+ "tool_versions": {
65
+ "qairt": "2.42.0.251225135753_193295",
66
+ "onnx_runtime": "1.24.3"
67
+ },
68
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_7gen4.zip"
69
+ },
70
+ "voice_ai": {
71
+ "tool_versions": {
72
+ "qairt": "2.45.0.260326154327"
73
+ },
74
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_7gen4.zip"
75
+ }
76
+ },
77
+ "qualcomm-snapdragon-8-elite-gen5": {
78
+ "qnn_context_binary": {
79
+ "tool_versions": {
80
+ "qairt": "2.45.0.260326154327"
81
+ },
82
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_8_elite_gen5.zip"
83
+ },
84
+ "precompiled_qnn_onnx": {
85
+ "tool_versions": {
86
+ "qairt": "2.42.0.251225135753_193295",
87
+ "onnx_runtime": "1.24.3"
88
+ },
89
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_8_elite_gen5.zip"
90
+ },
91
+ "voice_ai": {
92
+ "tool_versions": {
93
+ "qairt": "2.45.0.260326154327"
94
+ },
95
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_8_elite_gen5.zip"
96
+ }
97
+ },
98
+ "qualcomm-snapdragon-x-elite": {
99
+ "qnn_context_binary": {
100
+ "tool_versions": {
101
+ "qairt": "2.45.0.260326154327"
102
+ },
103
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x_elite.zip"
104
+ },
105
+ "precompiled_qnn_onnx": {
106
+ "tool_versions": {
107
+ "qairt": "2.42.0.251225135753_193295",
108
+ "onnx_runtime": "1.24.3"
109
+ },
110
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x_elite.zip"
111
+ },
112
+ "voice_ai": {
113
+ "tool_versions": {
114
+ "qairt": "2.45.0.260326154327"
115
+ },
116
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_x_elite.zip"
117
+ }
118
+ },
119
+ "qualcomm-snapdragon-x2-elite": {
120
+ "qnn_context_binary": {
121
+ "tool_versions": {
122
+ "qairt": "2.45.0.260326154327"
123
+ },
124
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_snapdragon_x2_elite.zip"
125
+ },
126
+ "precompiled_qnn_onnx": {
127
+ "tool_versions": {
128
+ "qairt": "2.42.0.251225135753_193295",
129
+ "onnx_runtime": "1.24.3"
130
+ },
131
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_snapdragon_x2_elite.zip"
132
+ },
133
+ "voice_ai": {
134
+ "tool_versions": {
135
+ "qairt": "2.45.0.260326154327"
136
+ },
137
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_snapdragon_x2_elite.zip"
138
+ }
139
+ },
140
+ "qualcomm-sa7255p": {
141
+ "qnn_context_binary": {
142
+ "tool_versions": {
143
+ "qairt": "2.45.0.260326154327"
144
+ },
145
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa7255p.zip"
146
+ },
147
+ "voice_ai": {
148
+ "tool_versions": {
149
+ "qairt": "2.45.0.260326154327"
150
+ },
151
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa7255p.zip"
152
+ }
153
+ },
154
+ "qualcomm-sa8775p": {
155
+ "qnn_context_binary": {
156
+ "tool_versions": {
157
+ "qairt": "2.45.0.260326154327"
158
+ },
159
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_sa8775p.zip"
160
+ },
161
+ "voice_ai": {
162
+ "tool_versions": {
163
+ "qairt": "2.45.0.260326154327"
164
+ },
165
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_sa8775p.zip"
166
+ }
167
+ },
168
+ "qualcomm-qcm6690": {
169
+ "qnn_context_binary": {
170
+ "tool_versions": {
171
+ "qairt": "2.45.0.260326154327"
172
+ },
173
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcm6690.zip"
174
+ },
175
+ "precompiled_qnn_onnx": {
176
+ "tool_versions": {
177
+ "qairt": "2.42.0.251225135753_193295",
178
+ "onnx_runtime": "1.24.3"
179
+ },
180
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcm6690.zip"
181
+ },
182
+ "voice_ai": {
183
+ "tool_versions": {
184
+ "qairt": "2.45.0.260326154327"
185
+ },
186
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcm6690.zip"
187
+ }
188
+ },
189
+ "qualcomm-qcs8550-proxy": {
190
+ "qnn_context_binary": {
191
+ "tool_versions": {
192
+ "qairt": "2.45.0.260326154327"
193
+ },
194
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs8550_proxy.zip"
195
+ },
196
+ "precompiled_qnn_onnx": {
197
+ "tool_versions": {
198
+ "qairt": "2.42.0.251225135753_193295",
199
+ "onnx_runtime": "1.24.3"
200
+ },
201
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs8550_proxy.zip"
202
+ },
203
+ "voice_ai": {
204
+ "tool_versions": {
205
+ "qairt": "2.45.0.260326154327"
206
+ },
207
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs8550_proxy.zip"
208
+ }
209
+ },
210
+ "qualcomm-qcs9075": {
211
+ "qnn_context_binary": {
212
+ "tool_versions": {
213
+ "qairt": "2.45.0.260326154327"
214
+ },
215
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-qnn_context_binary-w8a16-qualcomm_qcs9075.zip"
216
+ },
217
+ "precompiled_qnn_onnx": {
218
+ "tool_versions": {
219
+ "qairt": "2.42.0.251225135753_193295",
220
+ "onnx_runtime": "1.24.3"
221
+ },
222
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-precompiled_qnn_onnx-w8a16-qualcomm_qcs9075.zip"
223
+ },
224
+ "voice_ai": {
225
+ "tool_versions": {
226
+ "qairt": "2.45.0.260326154327"
227
+ },
228
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small_quantized/releases/v0.51.0/whisper_small_quantized-voice_ai-w8a16-qualcomm_qcs9075.zip"
229
+ }
230
+ }
231
+ }
232
+ }
233
+ }
234
+ }