Hugging Face's logo

qualcomm
/
Whisper-Small-Quantized

Automatic Speech Recognition
PyTorch
foundation
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
e462126
·
verified ·
1 Parent(s): c432984

v0.44.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.44.0 for changelog.

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. LICENSE +0 -1
  2. README.md +42 -39
  3. DEPLOYMENT_MODEL_LICENSE.pdf → precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  4. precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +3 -0
  5. precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +3 -0
  6. precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +3 -0
  7. precompiled/qualcomm-qcm6690/tool-versions.yaml +4 -0
  8. precompiled/qualcomm-qcs6490/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  9. precompiled/qualcomm-qcs6490/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +2 -2
  10. precompiled/qualcomm-qcs8275-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  11. precompiled/qualcomm-qcs8275-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  12. precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml +1 -1
  13. precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  14. precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  15. precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  16. precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +2 -2
  17. precompiled/qualcomm-qcs9075-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  18. precompiled/qualcomm-qcs9075-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  19. precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml +1 -1
  20. precompiled/qualcomm-sa7255p/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  21. precompiled/qualcomm-sa7255p/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  22. precompiled/qualcomm-sa7255p/tool-versions.yaml +1 -1
  23. precompiled/qualcomm-sa8255p-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  24. precompiled/qualcomm-sa8255p-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  25. precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml +1 -1
  26. precompiled/qualcomm-sa8650p-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  27. precompiled/qualcomm-sa8650p-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  28. precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml +1 -1
  29. precompiled/qualcomm-sa8775p/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  30. precompiled/qualcomm-sa8775p/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  31. precompiled/qualcomm-sa8775p/tool-versions.yaml +1 -1
  32. precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  33. precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  34. precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  35. precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +2 -2
  36. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  37. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  38. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  39. precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +2 -2
  40. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  41. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  42. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  43. precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +2 -2
  44. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  45. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  46. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
  47. precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip +2 -2
  48. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin +2 -2
  49. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip +2 -2
  50. precompiled/qualcomm-snapdragon-x-elite/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin +2 -2
LICENSE CHANGED
@@ -1,2 +1 @@
1
  The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE.
2
- The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
 
1
  The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE.
 
README.md CHANGED
@@ -35,44 +35,48 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | WhisperSmallEncoderQuantizable | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | PRECOMPILED_QNN_ONNX | 537.889 ms | 30 - 33 MB | NPU | Use Export Script |
39
- | WhisperSmallEncoderQuantizable | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 458.786 ms | 1 - 10 MB | NPU | Use Export Script |
40
- | WhisperSmallEncoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 353.084 ms | 1 - 3 MB | NPU | Use Export Script |
41
- | WhisperSmallEncoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 62.712 ms | 0 - 113 MB | NPU | Use Export Script |
42
- | WhisperSmallEncoderQuantizable | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 267.301 ms | 1 - 10 MB | NPU | Use Export Script |
43
- | WhisperSmallEncoderQuantizable | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 458.786 ms | 1 - 10 MB | NPU | Use Export Script |
44
- | WhisperSmallEncoderQuantizable | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 335.324 ms | 1 - 3 MB | NPU | Use Export Script |
45
- | WhisperSmallEncoderQuantizable | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 330.105 ms | 1 - 2 MB | NPU | Use Export Script |
46
- | WhisperSmallEncoderQuantizable | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 267.301 ms | 1 - 10 MB | NPU | Use Export Script |
47
- | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 250.011 ms | 1 - 19 MB | NPU | Use Export Script |
48
- | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 44.505 ms | 64 - 82 MB | NPU | Use Export Script |
49
- | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 202.875 ms | 1 - 14 MB | NPU | Use Export Script |
50
- | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 35.201 ms | 63 - 78 MB | NPU | Use Export Script |
51
- | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_CONTEXT_BINARY | 526.452 ms | 3 - 17 MB | NPU | Use Export Script |
52
- | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | PRECOMPILED_QNN_ONNX | 183.764 ms | 63 - 77 MB | NPU | Use Export Script |
53
- | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 179.19 ms | 1 - 11 MB | NPU | Use Export Script |
54
- | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 29.961 ms | 62 - 73 MB | NPU | Use Export Script |
55
- | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 243.159 ms | 0 - 0 MB | NPU | Use Export Script |
56
- | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 61.68 ms | 107 - 107 MB | NPU | Use Export Script |
57
- | WhisperSmallDecoderQuantizable | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | PRECOMPILED_QNN_ONNX | 32.659 ms | 27 - 59 MB | NPU | Use Export Script |
58
- | WhisperSmallDecoderQuantizable | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 13.485 ms | 29 - 39 MB | NPU | Use Export Script |
59
- | WhisperSmallDecoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 8.416 ms | 27 - 29 MB | NPU | Use Export Script |
60
- | WhisperSmallDecoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 8.737 ms | 0 - 193 MB | NPU | Use Export Script |
61
- | WhisperSmallDecoderQuantizable | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 9.562 ms | 27 - 37 MB | NPU | Use Export Script |
62
- | WhisperSmallDecoderQuantizable | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 13.485 ms | 29 - 39 MB | NPU | Use Export Script |
63
- | WhisperSmallDecoderQuantizable | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 8.495 ms | 27 - 29 MB | NPU | Use Export Script |
64
- | WhisperSmallDecoderQuantizable | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 8.279 ms | 34 - 37 MB | NPU | Use Export Script |
65
- | WhisperSmallDecoderQuantizable | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 9.562 ms | 27 - 37 MB | NPU | Use Export Script |
66
- | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 6.409 ms | 30 - 49 MB | NPU | Use Export Script |
67
- | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 6.785 ms | 38 - 57 MB | NPU | Use Export Script |
68
- | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 4.763 ms | 21 - 38 MB | NPU | Use Export Script |
69
- | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 5.095 ms | 26 - 39 MB | NPU | Use Export Script |
70
- | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_CONTEXT_BINARY | 11.037 ms | 30 - 45 MB | NPU | Use Export Script |
71
- | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | PRECOMPILED_QNN_ONNX | 11.94 ms | 30 - 43 MB | NPU | Use Export Script |
72
- | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 4.012 ms | 30 - 42 MB | NPU | Use Export Script |
73
- | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 4.368 ms | 37 - 48 MB | NPU | Use Export Script |
74
- | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 7.725 ms | 30 - 30 MB | NPU | Use Export Script |
75
- | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 7.841 ms | 186 - 186 MB | NPU | Use Export Script |
 
 
 
 
76
 
77
 
78
 
@@ -159,7 +163,6 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
159
  ## License
160
  * The license for the original implementation of Whisper-Small-Quantized can be found
161
  [here](https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE).
162
- * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
163
 
164
 
165
 
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | WhisperSmallEncoderQuantizable | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | QNN_CONTEXT_BINARY | 4274.97 ms | 1 - 14 MB | NPU | Use Export Script |
39
+ | WhisperSmallEncoderQuantizable | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | PRECOMPILED_QNN_ONNX | 1576.21 ms | 2 - 16 MB | NPU | Use Export Script |
40
+ | WhisperSmallEncoderQuantizable | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | PRECOMPILED_QNN_ONNX | 538.969 ms | 48 - 51 MB | NPU | Use Export Script |
41
+ | WhisperSmallEncoderQuantizable | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 463.377 ms | 1 - 9 MB | NPU | Use Export Script |
42
+ | WhisperSmallEncoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 307.27 ms | 1 - 4 MB | NPU | Use Export Script |
43
+ | WhisperSmallEncoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 61.701 ms | 63 - 65 MB | NPU | Use Export Script |
44
+ | WhisperSmallEncoderQuantizable | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 270.353 ms | 1 - 10 MB | NPU | Use Export Script |
45
+ | WhisperSmallEncoderQuantizable | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 463.377 ms | 1 - 9 MB | NPU | Use Export Script |
46
+ | WhisperSmallEncoderQuantizable | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 345.284 ms | 1 - 3 MB | NPU | Use Export Script |
47
+ | WhisperSmallEncoderQuantizable | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 331.302 ms | 1 - 3 MB | NPU | Use Export Script |
48
+ | WhisperSmallEncoderQuantizable | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 270.353 ms | 1 - 10 MB | NPU | Use Export Script |
49
+ | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 250.146 ms | 1 - 18 MB | NPU | Use Export Script |
50
+ | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 45.286 ms | 63 - 82 MB | NPU | Use Export Script |
51
+ | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 207.463 ms | 1 - 17 MB | NPU | Use Export Script |
52
+ | WhisperSmallEncoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 36.987 ms | 63 - 77 MB | NPU | Use Export Script |
53
+ | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_CONTEXT_BINARY | 527.982 ms | 0 - 13 MB | NPU | Use Export Script |
54
+ | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | PRECOMPILED_QNN_ONNX | 187.371 ms | 53 - 63 MB | NPU | Use Export Script |
55
+ | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 197.418 ms | 1 - 12 MB | NPU | Use Export Script |
56
+ | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 27.177 ms | 62 - 73 MB | NPU | Use Export Script |
57
+ | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 245.094 ms | 0 - 0 MB | NPU | Use Export Script |
58
+ | WhisperSmallEncoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 61.585 ms | 107 - 107 MB | NPU | Use Export Script |
59
+ | WhisperSmallDecoderQuantizable | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | QNN_CONTEXT_BINARY | 40.815 ms | 30 - 44 MB | NPU | Use Export Script |
60
+ | WhisperSmallDecoderQuantizable | w8a16 | Dragonwing Q-6690 MTP | Qualcomm® Qcm6690 | PRECOMPILED_QNN_ONNX | 31.387 ms | 39 - 52 MB | NPU | Use Export Script |
61
+ | WhisperSmallDecoderQuantizable | w8a16 | Dragonwing RB3 Gen 2 Vision Kit | Qualcomm® QCS6490 | PRECOMPILED_QNN_ONNX | 31.995 ms | 29 - 62 MB | NPU | Use Export Script |
62
+ | WhisperSmallDecoderQuantizable | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_CONTEXT_BINARY | 13.519 ms | 26 - 34 MB | NPU | Use Export Script |
63
+ | WhisperSmallDecoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_CONTEXT_BINARY | 8.418 ms | 30 - 34 MB | NPU | Use Export Script |
64
+ | WhisperSmallDecoderQuantizable | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | PRECOMPILED_QNN_ONNX | 8.647 ms | 29 - 31 MB | NPU | Use Export Script |
65
+ | WhisperSmallDecoderQuantizable | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_CONTEXT_BINARY | 9.426 ms | 25 - 34 MB | NPU | Use Export Script |
66
+ | WhisperSmallDecoderQuantizable | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_CONTEXT_BINARY | 13.519 ms | 26 - 34 MB | NPU | Use Export Script |
67
+ | WhisperSmallDecoderQuantizable | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_CONTEXT_BINARY | 8.309 ms | 30 - 33 MB | NPU | Use Export Script |
68
+ | WhisperSmallDecoderQuantizable | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_CONTEXT_BINARY | 8.365 ms | 30 - 33 MB | NPU | Use Export Script |
69
+ | WhisperSmallDecoderQuantizable | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_CONTEXT_BINARY | 9.426 ms | 25 - 34 MB | NPU | Use Export Script |
70
+ | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 6.396 ms | 14 - 32 MB | NPU | Use Export Script |
71
+ | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | PRECOMPILED_QNN_ONNX | 6.819 ms | 38 - 57 MB | NPU | Use Export Script |
72
+ | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_CONTEXT_BINARY | 4.744 ms | 28 - 44 MB | NPU | Use Export Script |
73
+ | WhisperSmallDecoderQuantizable | w8a16 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | PRECOMPILED_QNN_ONNX | 5.144 ms | 26 - 37 MB | NPU | Use Export Script |
74
+ | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | QNN_CONTEXT_BINARY | 11.215 ms | 32 - 46 MB | NPU | Use Export Script |
75
+ | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 7 Gen 4 QRD | Snapdragon® 7 Gen 4 Mobile | PRECOMPILED_QNN_ONNX | 11.984 ms | 38 - 52 MB | NPU | Use Export Script |
76
+ | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | QNN_CONTEXT_BINARY | 3.992 ms | 28 - 39 MB | NPU | Use Export Script |
77
+ | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | PRECOMPILED_QNN_ONNX | 4.418 ms | 36 - 46 MB | NPU | Use Export Script |
78
+ | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 7.669 ms | 30 - 30 MB | NPU | Use Export Script |
79
+ | WhisperSmallDecoderQuantizable | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | PRECOMPILED_QNN_ONNX | 7.777 ms | 186 - 186 MB | NPU | Use Export Script |
80
 
81
 
82
 
 
163
  ## License
164
  * The license for the original implementation of Whisper-Small-Quantized can be found
165
  [here](https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE).
 
166
 
167
 
168
 
DEPLOYMENT_MODEL_LICENSE.pdf → precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
- size 109629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:327e49de3f5eccfc17ad8e57e1da85c1ad54f583d20705495e1dafcb21701cf6
3
+ size 225636352
precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0ac107e9e0624de5cf8d834067a8e8c26c185cb8138d391c3541b68964df2c
3
+ size 193700590
precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9896983d0899141305703f60b387e09d190f3e531d2269f0acb732fa4c557ea5
3
+ size 187011072
precompiled/qualcomm-qcm6690/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1576c2abba6350944ea4b913125cf2bc7e9ebdb7e25d635344c8ad5c1559873
3
+ size 101219746
precompiled/qualcomm-qcm6690/tool-versions.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ tool_versions:
2
+ precompiled_qnn_onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
+ onnx_runtime: 1.23.0
precompiled/qualcomm-qcs6490/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57600c23f629dc4856253125f2247a207654d6c0109847f3cfe77d2aa7294774
3
- size 193518242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5ae1ce2b117ba20a21b1517046729199a8bdd24c233884547901aed115704d
3
+ size 193518277
precompiled/qualcomm-qcs6490/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00219edb3cfbfd14364f2c3324a7c9201e27e12e1a70d265b162f23da1ca831c
3
- size 102104981
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b61f928340aa452b86362c93f3c793e2765d39cb44a9f7eb5e66d50c687d316
3
+ size 102105014
precompiled/qualcomm-qcs8275-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24208db19866047ea5ad231d2836f469283e3f637e8b024ff42be251e6c0bdcf
3
- size 225382400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8eb26090b3d6422daa3a666425c30aa5e969ea71ef5b92a5c7ed044d32181c
3
+ size 225398784
precompiled/qualcomm-qcs8275-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4794729267b57f8d32ce5ba27a3419f395db5c1f02c8d4dbdf3b6f7971004e8d
3
- size 130682880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3716719e2e4cc9c5392b7c97f6dbcaa6d0edae6ca065b86ce7b1ee1481e6c29e
3
+ size 133246976
precompiled/qualcomm-qcs8275-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.40.0.251030114326_189385-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.41.0.251128145156_191518-auto
precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10394e71510154ed77feae4dc48450d289685a1eee515fbd5f5655541c908ef8
3
- size 225378304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14e04ef879365480fc0eaff9e62ad034218a39556aedc5339af70f626ace650
3
+ size 225398784
precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47054c0afebadfb456f3a5307731b6e85dd20aa6d2c8b01d80f59296cdd65783
3
- size 193590918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2743abf41feb89901646354c21d473ca2899d986b1f09c1c00649041db1d26d7
3
+ size 193590953
precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79df9e8e3a94e3923bf5ae03a60bf4622e28bdf60153246a9336867655b9664c
3
- size 130580480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dc49f9dcceb42232eaf1d3b25db49b85863ef3b9c7128483f6be031766e351
3
+ size 133283840
precompiled/qualcomm-qcs8550-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:127854ee8c90c814a983e5a1cb4faee1a2661d8e4640c99e50b66ca231156225
3
- size 93996909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1f3c49afa25d840672c732f1b340daf0e094b3556823eb95d26d4aa369ce79
3
+ size 93996941
precompiled/qualcomm-qcs9075-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1843626282087293ceb96dbfe14e5c80689f33b4658c6887092d35b881b0be00
3
- size 225386496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614760733160982e6b1bd776f85f0159b5212a7a12b6996e4286d6c823d09640
3
+ size 225402880
precompiled/qualcomm-qcs9075-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef0733e4636f075193280ac4d3c1beabf6b5b6b4603369ce89b7cf726fd39028
3
- size 130678784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cdc84e13d269451e56965335680e1317dc6d2658949de51c5a10aae416aa94
3
+ size 133292032
precompiled/qualcomm-qcs9075-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.40.0.251030114326_189385-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.41.0.251128145156_191518-auto
precompiled/qualcomm-sa7255p/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24208db19866047ea5ad231d2836f469283e3f637e8b024ff42be251e6c0bdcf
3
- size 225382400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8eb26090b3d6422daa3a666425c30aa5e969ea71ef5b92a5c7ed044d32181c
3
+ size 225398784
precompiled/qualcomm-sa7255p/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4794729267b57f8d32ce5ba27a3419f395db5c1f02c8d4dbdf3b6f7971004e8d
3
- size 130682880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3716719e2e4cc9c5392b7c97f6dbcaa6d0edae6ca065b86ce7b1ee1481e6c29e
3
+ size 133246976
precompiled/qualcomm-sa7255p/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.40.0.251030114326_189385-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.41.0.251128145156_191518-auto
precompiled/qualcomm-sa8255p-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10394e71510154ed77feae4dc48450d289685a1eee515fbd5f5655541c908ef8
3
- size 225378304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14e04ef879365480fc0eaff9e62ad034218a39556aedc5339af70f626ace650
3
+ size 225398784
precompiled/qualcomm-sa8255p-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79df9e8e3a94e3923bf5ae03a60bf4622e28bdf60153246a9336867655b9664c
3
- size 130580480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dc49f9dcceb42232eaf1d3b25db49b85863ef3b9c7128483f6be031766e351
3
+ size 133283840
precompiled/qualcomm-sa8255p-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.40.0.251030114326_189385
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.41.0.251128145156_191518
precompiled/qualcomm-sa8650p-proxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10394e71510154ed77feae4dc48450d289685a1eee515fbd5f5655541c908ef8
3
- size 225378304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b14e04ef879365480fc0eaff9e62ad034218a39556aedc5339af70f626ace650
3
+ size 225398784
precompiled/qualcomm-sa8650p-proxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79df9e8e3a94e3923bf5ae03a60bf4622e28bdf60153246a9336867655b9664c
3
- size 130580480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09dc49f9dcceb42232eaf1d3b25db49b85863ef3b9c7128483f6be031766e351
3
+ size 133283840
precompiled/qualcomm-sa8650p-proxy/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.40.0.251030114326_189385
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.41.0.251128145156_191518
precompiled/qualcomm-sa8775p/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1843626282087293ceb96dbfe14e5c80689f33b4658c6887092d35b881b0be00
3
- size 225386496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:614760733160982e6b1bd776f85f0159b5212a7a12b6996e4286d6c823d09640
3
+ size 225402880
precompiled/qualcomm-sa8775p/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef0733e4636f075193280ac4d3c1beabf6b5b6b4603369ce89b7cf726fd39028
3
- size 130678784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5cdc84e13d269451e56965335680e1317dc6d2658949de51c5a10aae416aa94
3
+ size 133292032
precompiled/qualcomm-sa8775p/tool-versions.yaml CHANGED
@@ -1,3 +1,3 @@
1
  tool_versions:
2
  qnn_context_binary:
3
- qairt: 2.40.0.251030114326_189385-auto
 
1
  tool_versions:
2
  qnn_context_binary:
3
+ qairt: 2.41.0.251128145156_191518-auto
precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c4e5b2c9d14cbd89276b447dafe01c47c469125b1c106581c4975095069d1c0
3
- size 225513472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74245f6b7c58877881e8d369ae33dc13d012c56602eaefc8fc5b2beb6cdc2819
3
+ size 225529856
precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb1783b340467387cc5d85f83cd80c8dd349cb45a1d96198ac619d89bc0cac02
3
- size 193634987
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0916b277fb90a3c07dad30bb9beb6c140bcf888acf56edcce7ceafc32c4593a3
3
+ size 193635048
precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d77d64e8b1b4f3d7c9646f9bbc9131d594ab70a9b85fab3a5e9b6779e5e5023c
3
- size 145821696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad65c8a6005f43d940643ff038c557ebbdbdb43176534649c7f022095247e05
3
+ size 148570112
precompiled/qualcomm-snapdragon-7gen4/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c22175c3ad26cb22386a78a5a5054b2daeb175d730eb4bea2f0802fd9a43c43
3
- size 110006846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12baef1fe946ce8d744540d1b22d707a1a19eb07bb9224bd5d7d78e212932f91
3
+ size 110006863
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25fe4234de1f21dc4f86e5d9e892eaf408f14353c0c1d9d26f46c7c87d2d699c
3
- size 225320960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8d2b98ec0fa9d9da9b66a08d146cb963a6ac166deb050015c3dd3bebbbb9ae
3
+ size 225337344
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cdb0c0d3d01a30aa44fb67e66c5dea4e1b3f8d2120e585ce007037986ddd18a
3
- size 193571498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8790539ce7cde56dbe2abdeb0924b98b53d5aef97365f56d4e9f0d3f48c03a81
3
+ size 193571532
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad0e827e028aa01bc8efd4b4286ec3763f094e580903521a1f4276a3a3d1280d
3
- size 129683456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2982c900161091b822c93a9df0015747158a75b1c0d71a66b84752205319e69
3
+ size 132247552
precompiled/qualcomm-snapdragon-8-elite-for-galaxy/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4a744302a5f4b99676d7635a06559c1db1c09fdf8987446d9289c98af6cb6f0
3
- size 93686223
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347377a0d2ef7eb652daa764da911fe9b9ea7bbbc7e6d600ecbda8fc35117f31
3
+ size 93686254
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ae8c828515e159b8c6d31acdd6df36a40a2511a48bb7a743e54e9f8fbb399ec
3
- size 225484800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0ab87882d54b304bf0bf571faacf4f4582c1d22d6288254622424c8be9776e
3
+ size 225501184
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92d4a8126793b548f06288a69a39b254ae66c5cce965e5b4b5b97dbe450cd863
3
- size 193623918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83aec4b198ddab15656a6d19fd829da5a8f4751fb736e4030d4c8d269d725e19
3
+ size 193623914
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68440264fd98da6dff55960c62385e3e7cf8ecf1bcf151eeab3221dba24d7ff4
3
- size 132378624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a06f93abf396762e762e3d23681d21f5f1bf7234b5c7ee1110d3cc1485a713d
3
+ size 134934528
precompiled/qualcomm-snapdragon-8-elite-gen5/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dcbb02351bf80700db43546fe688ea377b24608d7534f9cf14d25db8876c505
3
- size 94065502
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60312b0a9da5341fb1abe1a59dc77e59ab1b3def63625b798596b8cab14ae40f
3
+ size 94065534
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ce55c7368a2022bbef3070e71d2fb52a112f46581b371344cba209081ad7b10
3
- size 225374208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c2192993bfda4acba4348fa9aa51fdf3055c4cf6992a584bfd82f5300d1225
3
+ size 225390592
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ac956625f5fe8b00e208941c8d49b02900615b5c82abc2cec08d5aaedbbd736
3
- size 193588683
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c7a9f9491d6e613cd429a4610a266f3ab536175903c985b4f0817374318b400
3
+ size 193588834
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7da541c27e91456e766d6d1caeec55075a9353397d74cd0deaf36ab1db6c2183
3
- size 130445312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6550d3ded85ef93542017fd8db5a69d272c486802442adaa47b85900ab1f348
3
+ size 133124096
precompiled/qualcomm-snapdragon-8gen3/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e211aa7364781f5978537422f5d254f24ba8257212ea4646688c8c5195bac33d
3
- size 93711025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e877249f701849ee715838fc1676418aa9de2b32a1b7d9aedaafba1ec981e6b4
3
+ size 93711057
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c923fdd7d2606ef14af381b451faf9424ab6084840810b4434168a35533fb5f
3
- size 225378304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5413fd0496a104e4f470f76fef9028f5a6200482bd33f647549065e7f18b69c2
3
+ size 225398784
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small-Quantized_WhisperSmallDecoderQuantizable_w8a16.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aad1deba5891fc49ab797a80a58d16003a6178ccd33c0911331556f59bff53ea
3
- size 193589979
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad2e0bf28380928ed2f5549ad90a8d3b85bd11484c324ed252ea79904bc4d5c
3
+ size 193590013
precompiled/qualcomm-snapdragon-x-elite/Whisper-Small-Quantized_WhisperSmallEncoderQuantizable_w8a16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3c2fd6eaaf562d85a24b60017510a58849597abadc416f7684f0ed7692a6522
3
- size 130580480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e38113bb8548b9fb53f302fea907551e37eeccaa78f13ac9707adb5e5ec0c257
3
+ size 133283840