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
625653e
·
verified ·
1 Parent(s): 38dd092

v0.42.0

Browse files

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

Files changed (2) hide show
  1. HuggingFace-WavLM-Base-Plus_float.onnx.zip +2 -2
  2. README.md +21 -21
HuggingFace-WavLM-Base-Plus_float.onnx.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec751603437235ffe98a03c1b8cc441d937cb90fda7da9b34e371ccb3ae725bf
3
- size 347488614
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a3d07f51d24e04fbf6e037bd86a573d1d6611a91d36aff9bce036c0953e0c9
3
+ size 347488630
README.md CHANGED
@@ -36,23 +36,23 @@ 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 | 2873.641 ms | 125 - 883 MB | CPU | [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 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2004.027 ms | 122 - 1326 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
41
- | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1496.41 ms | 125 - 129 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
42
- | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 289.66 ms | 0 - 272 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
43
- | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2268.626 ms | 125 - 882 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
44
- | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 2873.641 ms | 125 - 883 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
45
- | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1609.5 ms | 125 - 129 MB | CPU | [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 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2070.4 ms | 125 - 1029 MB | CPU | [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 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1575.874 ms | 125 - 129 MB | CPU | [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 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2268.626 ms | 125 - 882 MB | CPU | [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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1325.767 ms | 125 - 1147 MB | CPU | [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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 216.975 ms | 0 - 853 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
51
- | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1057.782 ms | 125 - 879 MB | CPU | [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 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 188.511 ms | 0 - 663 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
53
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 972.546 ms | 124 - 875 MB | CPU | [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 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 156.458 ms | 0 - 729 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
55
- | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 294.833 ms | 202 - 202 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
56
 
57
 
58
 
@@ -67,9 +67,9 @@ pip install "qai-hub-models[huggingface-wavlm-base-plus]"
67
  ```
68
 
69
 
70
- ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
71
 
72
- Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
73
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
74
 
75
  With this API token, you can configure your client to run models on the cloud
@@ -77,7 +77,7 @@ hosted devices.
77
  ```bash
78
  qai-hub configure --api_token API_TOKEN
79
  ```
80
- Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
81
 
82
 
83
 
@@ -188,7 +188,7 @@ With the output of the model, you can compute like PSNR, relative errors or
188
  spot check the output with expected output.
189
 
190
  **Note**: This on-device profiling and inference requires access to Qualcomm®
191
- AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
192
 
193
 
194
 
 
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 | 2838.353 ms | 125 - 908 MB | CPU | [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 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2031.449 ms | 125 - 1352 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
41
+ | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1743.775 ms | 125 - 128 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
42
+ | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 291.085 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) |
43
+ | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2232.667 ms | 125 - 908 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
44
+ | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 2838.353 ms | 125 - 908 MB | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
45
+ | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1662.966 ms | 125 - 129 MB | CPU | [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 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 2056.068 ms | 116 - 1044 MB | CPU | [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 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1695.741 ms | 125 - 191 MB | CPU | [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 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2232.667 ms | 125 - 908 MB | CPU | [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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1413.877 ms | 125 - 1173 MB | CPU | [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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 219.41 ms | 0 - 852 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
51
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 1054.762 ms | 125 - 903 MB | CPU | [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 | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 188.588 ms | 1 - 664 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
53
+ | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 888.997 ms | 123 - 901 MB | CPU | [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 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 154.713 ms | 0 - 728 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
55
+ | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 295.583 ms | 202 - 202 MB | NPU | [HuggingFace-WavLM-Base-Plus.onnx.zip](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx.zip) |
56
 
57
 
58
 
 
67
  ```
68
 
69
 
70
+ ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
71
 
72
+ Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
73
  Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
74
 
75
  With this API token, you can configure your client to run models on the cloud
 
77
  ```bash
78
  qai-hub configure --api_token API_TOKEN
79
  ```
80
+ Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
81
 
82
 
83
 
 
188
  spot check the output with expected output.
189
 
190
  **Note**: This on-device profiling and inference requires access to Qualcomm®
191
+ AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
192
 
193
 
194