Hugging Face's logo

qualcomm
/
Whisper-Small

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
8e1c878
·
verified ·
1 Parent(s): 628be4f

v0.42.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.42.0 for changelog.

Files changed (45) hide show
  1. README.md +40 -40
  2. precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  3. precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  4. precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml +1 -1
  5. precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperDecoder_float.bin +1 -1
  6. precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  7. precompiled/qualcomm-qcs8450-proxy/tool-versions.yaml +1 -1
  8. precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  9. precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder_float.onnx.zip +1 -1
  10. precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  11. precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder_float.onnx.zip +2 -2
  12. precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  13. precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  14. precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml +1 -1
  15. precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  16. precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  17. precompiled/qualcomm-sa7255p/tool-versions.yaml +1 -1
  18. precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  19. precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  20. precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml +1 -1
  21. precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperDecoder_float.bin +1 -1
  22. precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  23. precompiled/qualcomm-sa8295p/tool-versions.yaml +1 -1
  24. precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  25. precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  26. precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml +1 -1
  27. precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  28. precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  29. precompiled/qualcomm-sa8775p/tool-versions.yaml +1 -1
  30. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  31. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperDecoder_float.onnx.zip +1 -1
  32. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  33. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperEncoder_float.onnx.zip +2 -2
  34. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  35. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperDecoder_float.onnx.zip +2 -2
  36. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  37. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperEncoder_float.onnx.zip +2 -2
  38. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  39. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder_float.onnx.zip +2 -2
  40. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  41. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder_float.onnx.zip +2 -2
  42. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder_float.bin +2 -2
  43. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder_float.onnx.zip +2 -2
  44. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder_float.bin +2 -2
  45. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder_float.onnx.zip +2 -2
README.md CHANGED
@@ -39,42 +39,42 @@ More details on model performance across various devices, can be found
39
 
40
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
41
  |---|---|---|---|---|---|---|---|---|
42
- | HfWhisperEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 395.632 ms | 1 - 10 MB | NPU | Use Export Script |
43
- | HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 282.113 ms | 1 - 14 MB | NPU | Use Export Script |
44
- | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 116.38 ms | 1 - 3 MB | NPU | Use Export Script |
45
- | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 146.737 ms | 245 - 247 MB | NPU | Use Export Script |
46
- | HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 137.384 ms | 1 - 12 MB | NPU | Use Export Script |
47
- | HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 395.632 ms | 1 - 10 MB | NPU | Use Export Script |
48
- | HfWhisperEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 116.188 ms | 1 - 3 MB | NPU | Use Export Script |
49
- | HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 226.161 ms | 1 - 16 MB | NPU | Use Export Script |
50
- | HfWhisperEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 115.072 ms | 1 - 3 MB | NPU | Use Export Script |
51
- | HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 137.384 ms | 1 - 12 MB | NPU | Use Export Script |
52
- | HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 85.269 ms | 1 - 19 MB | NPU | Use Export Script |
53
- | HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 112.88 ms | 256 - 274 MB | NPU | Use Export Script |
54
- | HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 61.365 ms | 1 - 15 MB | NPU | Use Export Script |
55
- | HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 87.358 ms | 216 - 227 MB | NPU | Use Export Script |
56
- | HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 49.455 ms | 1 - 12 MB | NPU | Use Export Script |
57
- | HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 69.54 ms | 235 - 246 MB | NPU | Use Export Script |
58
- | HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 115.721 ms | 1 - 1 MB | NPU | Use Export Script |
59
- | HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 139.298 ms | 265 - 265 MB | NPU | Use Export Script |
60
- | HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 26.645 ms | 100 - 110 MB | NPU | Use Export Script |
61
- | HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 27.395 ms | 120 - 143 MB | NPU | Use Export Script |
62
- | HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 17.86 ms | 124 - 127 MB | NPU | Use Export Script |
63
- | HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 18.542 ms | 123 - 127 MB | NPU | Use Export Script |
64
- | HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 19.812 ms | 97 - 108 MB | NPU | Use Export Script |
65
- | HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 26.645 ms | 100 - 110 MB | NPU | Use Export Script |
66
- | HfWhisperDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 17.908 ms | 117 - 119 MB | NPU | Use Export Script |
67
- | HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 21.119 ms | 97 - 111 MB | NPU | Use Export Script |
68
- | HfWhisperDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 17.998 ms | 120 - 123 MB | NPU | Use Export Script |
69
- | HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 19.812 ms | 97 - 108 MB | NPU | Use Export Script |
70
- | HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 14.117 ms | 120 - 140 MB | NPU | Use Export Script |
71
- | HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 14.805 ms | 150 - 166 MB | NPU | Use Export Script |
72
- | HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 12.62 ms | 63 - 79 MB | NPU | Use Export Script |
73
- | HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 12.779 ms | 97 - 107 MB | NPU | Use Export Script |
74
- | HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 10.324 ms | 118 - 130 MB | NPU | Use Export Script |
75
- | HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 10.603 ms | 95 - 105 MB | NPU | Use Export Script |
76
- | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 14.905 ms | 120 - 120 MB | NPU | Use Export Script |
77
- | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 14.763 ms | 226 - 226 MB | NPU | Use Export Script |
78
 
79
 
80
 
@@ -89,9 +89,9 @@ pip install "qai-hub-models[whisper-small]"
89
  ```
90
 
91
 
92
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
93
 
94
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
95
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
96
 
97
  With this API token, you can configure your client to run models on the cloud
@@ -99,7 +99,7 @@ hosted devices.
99
  ```bash
100
  qai-hub configure --api_token API_TOKEN
101
  ```
102
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
103
 
104
 
105
 
@@ -210,7 +210,7 @@ With the output of the model, you can compute like PSNR, relative errors or
210
  spot check the output with expected output.
211
 
212
  **Note**: This on-device profiling and inference requires access to Qualcomm®
213
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
214
 
215
 
216
 
 
39
 
40
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
41
  |---|---|---|---|---|---|---|---|---|
42
+ | HfWhisperEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 399.405 ms | 1 - 11 MB | NPU | Use Export Script |
43
+ | HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 283.438 ms | 1 - 21 MB | NPU | Use Export Script |
44
+ | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 117.223 ms | 1 - 3 MB | NPU | Use Export Script |
45
+ | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 147.636 ms | 246 - 248 MB | NPU | Use Export Script |
46
+ | HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 137.869 ms | 1 - 12 MB | NPU | Use Export Script |
47
+ | HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 399.405 ms | 1 - 11 MB | NPU | Use Export Script |
48
+ | HfWhisperEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 117.805 ms | 0 - 3 MB | NPU | Use Export Script |
49
+ | HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 251.904 ms | 1 - 16 MB | NPU | Use Export Script |
50
+ | HfWhisperEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 116.146 ms | 1 - 3 MB | NPU | Use Export Script |
51
+ | HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 137.869 ms | 1 - 12 MB | NPU | Use Export Script |
52
+ | HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 83.84 ms | 1 - 16 MB | NPU | Use Export Script |
53
+ | HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 111.495 ms | 252 - 272 MB | NPU | Use Export Script |
54
+ | HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 62.439 ms | 1 - 15 MB | NPU | Use Export Script |
55
+ | HfWhisperEncoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 87.116 ms | 218 - 229 MB | NPU | Use Export Script |
56
+ | HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 49.58 ms | 0 - 11 MB | NPU | Use Export Script |
57
+ | HfWhisperEncoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 70.847 ms | 235 - 245 MB | NPU | Use Export Script |
58
+ | HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 116.219 ms | 1 - 1 MB | NPU | Use Export Script |
59
+ | HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 139.758 ms | 264 - 264 MB | NPU | Use Export Script |
60
+ | HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 26.449 ms | 94 - 103 MB | NPU | Use Export Script |
61
+ | HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_CONTEXT_BINARY | 26.871 ms | 115 - 133 MB | NPU | Use Export Script |
62
+ | HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 17.839 ms | 107 - 109 MB | NPU | Use Export Script |
63
+ | HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 18.303 ms | 118 - 120 MB | NPU | Use Export Script |
64
+ | HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 42.514 ms | 114 - 124 MB | NPU | Use Export Script |
65
+ | HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 26.449 ms | 94 - 103 MB | NPU | Use Export Script |
66
+ | HfWhisperDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 17.814 ms | 119 - 122 MB | NPU | Use Export Script |
67
+ | HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_CONTEXT_BINARY | 20.885 ms | 105 - 121 MB | NPU | Use Export Script |
68
+ | HfWhisperDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 17.694 ms | 120 - 122 MB | NPU | Use Export Script |
69
+ | HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 42.514 ms | 114 - 124 MB | NPU | Use Export Script |
70
+ | HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 13.933 ms | 114 - 133 MB | NPU | Use Export Script |
71
+ | HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 14.507 ms | 151 - 171 MB | NPU | Use Export Script |
72
+ | HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 12.564 ms | 68 - 82 MB | NPU | Use Export Script |
73
+ | HfWhisperDecoder | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 12.953 ms | 46 - 57 MB | NPU | Use Export Script |
74
+ | HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 10.249 ms | 120 - 131 MB | NPU | Use Export Script |
75
+ | HfWhisperDecoder | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 10.726 ms | 151 - 162 MB | NPU | Use Export Script |
76
+ | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 14.745 ms | 120 - 120 MB | NPU | Use Export Script |
77
+ | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 14.966 ms | 226 - 226 MB | NPU | Use Export Script |
78
 
79
 
80
 
 
89
  ```
90
 
91
 
92
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
93
 
94
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
95
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
96
 
97
  With this API token, you can configure your client to run models on the cloud
 
99
  ```bash
100
  qai-hub configure --api_token API_TOKEN
101
  ```
102
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
103
 
104
 
105
 
 
210
  spot check the output with expected output.
211
 
212
  **Note**: This on-device profiling and inference requires access to Qualcomm®
213
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
214
 
215
 
216
 
precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00f94a1b795c2ce38699fd39e54a8f6ec9556e79356341d735e6a3d75caed82c
3
- size 361566208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9f4ab77dfac8eddaf548ae702615ef4a87dffe8b1404f783786617855c4ec0
3
+ size 361558016
precompiled/qualcomm-qcs8275-proxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:647d3ad4025aaf71eb2c351ba44f74bff5eecc7e7bbaa83e8ed6b9d25d09b4d6
3
- size 211013632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a68ba2967b9fb0e1e7f0137fda568b52bf824ba6e0c9ad271feba3079f9ad5
3
+ size 211021824
precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385-auto
precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbaa531ca22385d8487bb16e0160b70f0888c2fe9e8a98a28beac5db4d25bf30
3
  size 359948288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac152baf2ae9891733a577f9303385b9f4dc24d4fe311f443b82bf5a0aef5c9b
3
  size 359948288
precompiled/qualcomm-qcs8450-proxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6a4e3b0b55cb21d3109a24d68b80f50e1528558789e9d9bb33257ec4ee0c6c0
3
- size 208842752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:601dff52d65cf854183c800d5e51b59fed72ff9ccc26d72fc397b203270110bc
3
+ size 208883712
precompiled/qualcomm-qcs8450-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385
precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc5e5aa0bc034c6567cc32e5018e67e726aff5c4a3bc7478b159a9f342f258e8
3
- size 361562112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750cb4655e26d51bf38892247426b3e5c8d98b1759bb114013bb41fd4b16fb77
3
+ size 361553920
precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperDecoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45a49283004f8492f3bbcd4dd9b056027bb0cb5cb47ba9b143d0f9a3179b34ca
3
  size 330477736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c1be25d78bc0fdc215e6d304c7bee41d234e8bb59c6b1a4dbb2a9f3a6d34520
3
  size 330477736
precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6bc34e6a916e97dd736ef00a5efbb9e7aec2992e01e0426192b8e2e5de1d7ea
3
- size 210935808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99483c407bbf429a5cdfd9367804d409c60330c4e183f3f4c94429cbdf11fe0
3
+ size 211046400
precompiled/qualcomm-qcs8550-proxy/Whisper-Small_HfWhisperEncoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20e8d20e33ecf9296d90fc1969571af06f9594a9075b4c6ca297c0fb88230a35
3
- size 198488852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf3651d233cd5b75ccfcfa21866f62abc151d11128d3874ba8449fb2f9362c77
3
+ size 198464257
precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4daedd6e9ba8153b7007973fc6f55c3d9a76fe365cdbd15804244839404bffa
3
- size 361566208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729577b426f50c3b3a2c1c6d34ad28e35734f591109c527b77a7d2fe70c3d0d5
3
+ size 361562112
precompiled/qualcomm-qcs9075-proxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2014490686df59e5d91c7e91406b9cb04447f01ad9d467002a8ec24e9f18a17e
3
- size 211001344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d26731c9d640afcab890d1f3b946b56de35c5b6cae9e59d936a1cfe224ee5fc
3
+ size 211021824
precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385-auto
precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00f94a1b795c2ce38699fd39e54a8f6ec9556e79356341d735e6a3d75caed82c
3
- size 361566208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9f4ab77dfac8eddaf548ae702615ef4a87dffe8b1404f783786617855c4ec0
3
+ size 361558016
precompiled/qualcomm-sa7255p/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:647d3ad4025aaf71eb2c351ba44f74bff5eecc7e7bbaa83e8ed6b9d25d09b4d6
3
- size 211013632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a68ba2967b9fb0e1e7f0137fda568b52bf824ba6e0c9ad271feba3079f9ad5
3
+ size 211021824
precompiled/qualcomm-sa7255p/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385-auto
precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc5e5aa0bc034c6567cc32e5018e67e726aff5c4a3bc7478b159a9f342f258e8
3
- size 361562112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750cb4655e26d51bf38892247426b3e5c8d98b1759bb114013bb41fd4b16fb77
3
+ size 361553920
precompiled/qualcomm-sa8255p-proxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9400a1e5098bbabd1f5ac7f98c64e76da6a8c5d1abd039d9970353d40a5f29fe
3
- size 210935808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777e54906bd8e9eda3c768f256bf4491ebc82b0fe022e4394c5683cc743a903c
3
+ size 211046400
precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385
precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:090fdf03636276b0db0ab1b56dfcf5a54a65cf977d4b1e41dba26e51fa8261bd
3
  size 359956480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458f44a191ddb495abb7ba8325e984f10846f36292d8bf1a1bc61b31b177140c
3
  size 359956480
precompiled/qualcomm-sa8295p/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5838e0f60aafa2352b9a0a0bc04711d54bf37a64b1486a411d44726332496088
3
- size 208871424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f801848476b4b933323e8c39b731a21985d37843a2c3118aef5e527dd79a9ba
3
+ size 208756736
precompiled/qualcomm-sa8295p/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385-auto
precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc5e5aa0bc034c6567cc32e5018e67e726aff5c4a3bc7478b159a9f342f258e8
3
- size 361562112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:750cb4655e26d51bf38892247426b3e5c8d98b1759bb114013bb41fd4b16fb77
3
+ size 361553920
precompiled/qualcomm-sa8650p-proxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bed9ee2bcaf008595cb9209b1925067c5a9f5038ca14c9fe1839ea93a3454f09
3
- size 210935808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99483c407bbf429a5cdfd9367804d409c60330c4e183f3f4c94429cbdf11fe0
3
+ size 211046400
precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385
precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4daedd6e9ba8153b7007973fc6f55c3d9a76fe365cdbd15804244839404bffa
3
- size 361566208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729577b426f50c3b3a2c1c6d34ad28e35734f591109c527b77a7d2fe70c3d0d5
3
+ size 361562112
precompiled/qualcomm-sa8775p/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2014490686df59e5d91c7e91406b9cb04447f01ad9d467002a8ec24e9f18a17e
3
- size 211001344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d26731c9d640afcab890d1f3b946b56de35c5b6cae9e59d936a1cfe224ee5fc
3
+ size 211021824
precompiled/qualcomm-sa8775p/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.39.0.250925215840_163802-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.40.0.251030114326_189385-auto
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b105230c82d31153733e638a7bed9f410124be39dc13ad53f3e56e3c9d863c88
3
- size 361664512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b015af9b57b8c07b23b6cf9af78603189d96aad62014a994d44abdc2dbe94d09
3
+ size 361660416
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperDecoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e0f7d13902b0ef0eb9bbc354fb939f9d568db03ab35e54fc2444f4cecc35fd9
3
  size 330508028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829e776caee50c9491f041a1c0a75194e732e55d31acb95f358965bec5c34fe2
3
  size 330508028
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bef8364b402a2959c93c526e98a2bfcc1d80ed1a31ab24c1c9332df67b4b91f3
3
- size 211251200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999d81089b473b03ce1f3f8f03a72b52fefbf501bb3c7fdf4207b5246632ffba
3
+ size 211320832
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small_HfWhisperEncoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52e870fb5c466762d67121729ebdaeb3e2d0eabc3c2087b93ec773642ee4fd4c
3
- size 198025273
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7202ef590725d4c83298a40dddb8541356a8c98ea29baa1d483d5201fa09fde0
3
+ size 198025329
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a31b31be464c9e0c1db53b3b3b1a8bee5afdae77300f86ed5dfa5380a4db2bbc
3
- size 361730048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5f687ee7a060a03a9cec105ab171800a8e18739a8d5e47a8e1238d65fcbccb6
3
+ size 361725952
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperDecoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba830312d9c6c7224e138e2b80b2966d8060e685a51ab74d63e7b0c38ac02ca3
3
- size 330536455
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e49a1d758b3d2972fb1e99c1625768ff2f55fb31691cfd840a4b7f3749592bfd
3
+ size 330536453
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96eb04fcbc7531b132ab3ff1581d281aaa40d6a44e018157a3cab376f24cc80e
3
- size 211906560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd11ea0f072946d82a654242fd4ab0547d6ac64c81594a468ee99a7e5aadcba8
3
+ size 212029440
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small_HfWhisperEncoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe6a4b1ec83141cad67e62af6343c6197424990bf9e4c1c19356dbeba80afe10
3
- size 197829071
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d1ae365c50372864bddccc4375d12b4e2fc3fa62af12692ce933be9827c528
3
+ size 197829044
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da23aafc8df980fff3c106c6b2cac2cbe8d3732a3732d21cedbb7f9678765b65
3
- size 361558016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b0379e2ca3a449e3cca5a3edf4929bf182d94ab29ead66568d4442ce58801a
3
+ size 361562112
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperDecoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db6860dc9f66f2432c46d22a213f2e525422c66c38e668ffa161789992c37ea4
3
- size 330490642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d54a0a657a7f987c9bce3f9822522237240900c77caf255791a5bae6a71dfb3
3
+ size 330490742
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45f47c3ca5c78caceb32246af58c9d841ba7bb3f6ef3cfe933e6b4acfe5818a7
3
- size 210989056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe7bb9b408f08d826727f911225b17fa7971b56f7a7e769a3c93829957a52dfa
3
+ size 211009536
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small_HfWhisperEncoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ecca1a1e44d0fed3f8c470b6c9fd8e99a1e49ca53bde21c581a139ed7cac9ca
3
- size 198477106
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:952a60d9bd5df9128fd12d4102599e8fbe8a62e0101edaeb9f25017a9e8c416e
3
+ size 198477268
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1faf05abd270230af4dfb812b8cbd209260bf6fe7245a72c0a699cc486f981cb
3
- size 361562112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d2bcb6a06cad8439d732c558408b300fde17553cb21e842cc4ca5040738ec54
3
+ size 361553920
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperDecoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51004266c4252431e200b803ce71779d484b68dea265b041d47768ea5511ae4e
3
- size 330477164
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:763e266d5885fc877ffae4d9ea1ce28a163908f1619e4e5d9195b96d9ce170f5
3
+ size 330477165
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder_float.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77067e7707d5eed049123b1270810b2c1ce7731f5217bd8002ee38e9151a2f71
3
- size 210935808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d1d62c67c09dcc0c1b875291caf06acff61a67abd5204d2ca4e9e2208d57d69
3
+ size 211046400
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small_HfWhisperEncoder_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f394e5b35a76e8eb1f2b0c47e8fef6939ca9a1b3b17d76adb9d63b0e1d7b1ee
3
- size 198430431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e27a4068b5b607869143f8a54807f000bb0eb932a4eec1958ebdea336646ee5
3
+ size 198440235