Hugging Face's logo

qualcomm
/
HuggingFace-WavLM-Base-Plus

Automatic Speech Recognition
PyTorch
LiteRT
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
13a4b2e
·
verified ·
1 Parent(s): 91effde

v0.38.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

Files changed (7) hide show
  1. HuggingFace-WavLM-Base-Plus_float.dlc +2 -2
  2. HuggingFace-WavLM-Base-Plus_float.onnx.zip +2 -2
  3. README.md +25 -30
  4. precompiled/qualcomm-snapdragon-x-elite/HuggingFace-WavLM-Base-Plus_float.bin +0 -3
  5. precompiled/qualcomm-snapdragon-x-elite/HuggingFace-WavLM-Base-Plus_float.onnx.zip +0 -3
  6. precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml +0 -3
  7. tool-versions.yaml +2 -2
HuggingFace-WavLM-Base-Plus_float.dlc CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c8c4ec824e67e69d91f2ac107d09fd20fdf213a627290f09a6aeb08d6fbc7cb
3
- size 390118308
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a5e7f83c0f8da0b4af5370cea5ae69475489c1d5be6071af81d065ccfcb8e5
3
+ size 390118396
HuggingFace-WavLM-Base-Plus_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a8e3d6d3e6345d8eae90017247e52ac19609658f7a52f7ac832ae2b248c1a92
3
- size 347488571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d449c0c0ead13a7877b69bdae88b9040fe30938bb2e9fb9c1f7336901b76f9b
3
+ size 347488614
README.md CHANGED
@@ -36,35 +36,30 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 799.175 ms | 0 - 769 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
40
- | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 851.51 ms | 1 - 767 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
41
- | HuggingFace-WavLM-Base-Plus | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 585.766 ms | 1 - 1134 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
42
- | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 246.813 ms | 0 - 54 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
43
- | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 288.379 ms | 0 - 47 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
44
- | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 470.796 ms | 0 - 274 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
45
- | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 297.214 ms | 0 - 769 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
46
- | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 315.873 ms | 1 - 770 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
47
- | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 799.175 ms | 0 - 769 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
48
- | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 851.51 ms | 1 - 767 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
49
- | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 252.816 ms | 0 - 55 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
50
- | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 292.383 ms | 0 - 47 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
51
- | HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 574.211 ms | 0 - 989 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
52
- | HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 438.776 ms | 87 - 1005 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
53
- | HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 251.051 ms | 0 - 55 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
54
- | HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 287.987 ms | 0 - 45 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
55
- | HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 297.214 ms | 0 - 769 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
56
- | HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 315.873 ms | 1 - 770 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
57
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 247.296 ms | 0 - 54 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
58
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 290.705 ms | 0 - 47 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
59
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 473.51 ms | 0 - 497 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
60
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 176.905 ms | 0 - 824 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
61
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 212.515 ms | 0 - 840 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
62
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 347.496 ms | 0 - 963 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
63
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 164.613 ms | 0 - 766 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
64
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 186.313 ms | 0 - 703 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
65
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 338.644 ms | 0 - 716 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
66
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 291.744 ms | 264 - 264 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
67
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 447.67 ms | 204 - 204 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
68
 
69
 
70
 
@@ -146,7 +141,7 @@ from qai_hub_models.models.huggingface_wavlm_base_plus import Model
146
  torch_model = Model.from_pretrained()
147
 
148
  # Device
149
- device = hub.Device("Samsung Galaxy S24")
150
 
151
  # Trace model
152
  input_shape = torch_model.get_input_spec()
 
36
 
37
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 802.748 ms | 0 - 775 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
40
+ | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 857.593 ms | 1 - 783 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
41
+ | HuggingFace-WavLM-Base-Plus | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 606.256 ms | 1 - 936 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
42
+ | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 254.045 ms | 0 - 54 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
43
+ | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 292.308 ms | 3 - 50 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
44
+ | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 431.332 ms | 0 - 270 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
45
+ | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 299.334 ms | 0 - 775 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
46
+ | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 802.748 ms | 0 - 775 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
47
+ | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 857.593 ms | 1 - 783 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
48
+ | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 254.961 ms | 0 - 52 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
49
+ | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 293.756 ms | 0 - 45 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
50
+ | HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 577.609 ms | 0 - 856 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
51
+ | HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 445.201 ms | 1 - 942 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
52
+ | HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 254.371 ms | 0 - 50 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
53
+ | HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 297.107 ms | 0 - 43 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
54
+ | HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 299.334 ms | 0 - 775 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
55
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 180.845 ms | 0 - 817 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
56
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 216.325 ms | 1 - 871 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
57
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 342.316 ms | 79 - 1004 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
58
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 141.131 ms | 0 - 770 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
59
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 187.723 ms | 1 - 677 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
60
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 284.47 ms | 1 - 741 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
61
+ | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 296.178 ms | 231 - 231 MB | NPU | [HuggingFace-WavLM-Base-Plus.dlc](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.dlc) |
62
+ | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 459.33 ms | 203 - 203 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
 
 
 
 
 
63
 
64
 
65
 
 
141
  torch_model = Model.from_pretrained()
142
 
143
  # Device
144
+ device = hub.Device("Samsung Galaxy S25")
145
 
146
  # Trace model
147
  input_shape = torch_model.get_input_spec()
precompiled/qualcomm-snapdragon-x-elite/HuggingFace-WavLM-Base-Plus_float.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c417f39e586c0a2d627030f353b3094c14e9357920f894b2db595d238ce162b
3
- size 211394560
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/HuggingFace-WavLM-Base-Plus_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b955d6ab668d3a6ef0e8a2d479f6c5d9d5ff717fff3448dda75dea86849e3de5
3
- size 180847349
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/tool-versions.yaml DELETED
@@ -1,3 +0,0 @@
1
- tool_versions:
2
- precompiled_qnn_onnx:
3
- qairt: 2.36.4.250725200057_123280
 
 
 
 
tool-versions.yaml CHANGED
@@ -1,4 +1,4 @@
1
  tool_versions:
2
  onnx:
3
- qairt: 2.36.4.250725200057_123280
4
- onnx_runtime: 1.22.0
 
1
  tool_versions:
2
  onnx:
3
+ qairt: 2.37.1.250807093845_124904
4
+ onnx_runtime: 1.22.2