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
647d5c7
·
verified ·
1 Parent(s): 6b98547

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +20 -21
README.md CHANGED
@@ -35,34 +35,32 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 163.393 ms | 0 - 54 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
39
- | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 177.655 ms | 3 - 152 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
40
- | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 122.842 ms | 1 - 197 MB | FP16 | NPU | [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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 131.58 ms | 3 - 732 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
42
- | HuggingFace-WavLM-Base-Plus | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 116.143 ms | 0 - 205 MB | FP16 | 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 97.142 ms | 2 - 754 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
44
- | HuggingFace-WavLM-Base-Plus | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 163.058 ms | 0 - 52 MB | FP16 | NPU | [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 | SA7255P ADP | SA7255P | TFLITE | 2268.61 ms | 0 - 203 MB | FP16 | 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 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 163.829 ms | 1 - 53 MB | FP16 | 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 | SA8295P ADP | SA8295P | TFLITE | 270.434 ms | 1 - 197 MB | FP16 | 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 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 163.843 ms | 0 - 57 MB | FP16 | 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 | SA8775P ADP | SA8775P | TFLITE | 224.911 ms | 1 - 204 MB | FP16 | 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 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 247.751 ms | 1 - 190 MB | FP16 | 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 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 185.374 ms | 206 - 206 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
52
 
53
 
54
 
55
 
56
  ## Installation
57
 
58
- This model can be installed as a Python package via pip.
59
 
 
60
  ```bash
61
- pip install "qai-hub-models[huggingface_wavlm_base_plus]"
62
  ```
63
 
64
 
65
-
66
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
67
 
68
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -113,8 +111,8 @@ Profiling Results
113
  HuggingFace-WavLM-Base-Plus
114
  Device : Samsung Galaxy S23 (13)
115
  Runtime : TFLITE
116
- Estimated inference time (ms) : 163.4
117
- Estimated peak memory usage (MB): [0, 54]
118
  Total # Ops : 871
119
  Compute Unit(s) : NPU (871 ops)
120
  ```
@@ -141,7 +139,7 @@ from qai_hub_models.models.huggingface_wavlm_base_plus import Model
141
  torch_model = Model.from_pretrained()
142
 
143
  # Device
144
- device = hub.Device("Samsung Galaxy S23")
145
 
146
  # Trace model
147
  input_shape = torch_model.get_input_spec()
@@ -219,7 +217,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
219
 
220
 
221
  ## License
222
- * The license for the original implementation of HuggingFace-WavLM-Base-Plus can be found [here](https://github.com/microsoft/unilm/blob/master/LICENSE).
 
223
  * 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)
224
 
225
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 165.096 ms | 0 - 49 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
39
+ | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 179.467 ms | 0 - 591 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
40
+ | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 120.933 ms | 0 - 194 MB | FP16 | NPU | [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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 130.638 ms | 2 - 730 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
42
+ | HuggingFace-WavLM-Base-Plus | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 99.04 ms | 0 - 204 MB | FP16 | 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 114.519 ms | 2 - 749 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
44
+ | HuggingFace-WavLM-Base-Plus | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 163.244 ms | 1 - 54 MB | FP16 | NPU | [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 | SA7255P ADP | SA7255P | TFLITE | 2268.66 ms | 0 - 203 MB | FP16 | 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 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 164.455 ms | 0 - 50 MB | FP16 | 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 | SA8295P ADP | SA8295P | TFLITE | 270.746 ms | 1 - 196 MB | FP16 | 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 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 163.808 ms | 0 - 64 MB | FP16 | 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 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 248.863 ms | 1 - 190 MB | FP16 | 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 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 185.941 ms | 206 - 206 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
 
51
 
52
 
53
 
54
 
55
  ## Installation
56
 
 
57
 
58
+ Install the package via pip:
59
  ```bash
60
+ pip install "qai-hub-models[huggingface-wavlm-base-plus]"
61
  ```
62
 
63
 
 
64
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
65
 
66
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
111
  HuggingFace-WavLM-Base-Plus
112
  Device : Samsung Galaxy S23 (13)
113
  Runtime : TFLITE
114
+ Estimated inference time (ms) : 165.1
115
+ Estimated peak memory usage (MB): [0, 49]
116
  Total # Ops : 871
117
  Compute Unit(s) : NPU (871 ops)
118
  ```
 
139
  torch_model = Model.from_pretrained()
140
 
141
  # Device
142
+ device = hub.Device("Samsung Galaxy S24")
143
 
144
  # Trace model
145
  input_shape = torch_model.get_input_spec()
 
217
 
218
 
219
  ## License
220
+ * The license for the original implementation of HuggingFace-WavLM-Base-Plus can be found
221
+ [here](https://github.com/microsoft/unilm/blob/master/LICENSE).
222
  * 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)
223
 
224