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
606eeb8
·
verified ·
1 Parent(s): 8510f87

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +9 -21
README.md CHANGED
@@ -35,22 +35,10 @@ 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 | 197.652 ms | 0 - 33 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 | 227.805 ms | 3 - 422 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 | 140.571 ms | 1 - 462 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 | 164.753 ms | 3 - 286 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 | 132.647 ms | 1 - 460 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 | 122.425 ms | 0 - 286 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 | SA7255P ADP | SA7255P | TFLITE | 2295.443 ms | 0 - 458 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 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 200.356 ms | 0 - 34 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 | SA8295P ADP | SA8295P | TFLITE | 307.069 ms | 1 - 519 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 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 203.02 ms | 0 - 34 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 | SA8775P ADP | SA8775P | TFLITE | 256.145 ms | 1 - 458 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 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 2295.443 ms | 0 - 458 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 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 197.979 ms | 0 - 37 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 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 256.145 ms | 1 - 458 MB | FP16 | 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 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 288.865 ms | 1 - 523 MB | FP16 | 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 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 233.997 ms | 197 - 197 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
54
 
55
 
56
 
@@ -113,11 +101,11 @@ Profiling Results
113
  ------------------------------------------------------------
114
  HuggingFace-WavLM-Base-Plus
115
  Device : Samsung Galaxy S23 (13)
116
- Runtime : TFLITE
117
- Estimated inference time (ms) : 197.7
118
- Estimated peak memory usage (MB): [0, 33]
119
- Total # Ops : 871
120
- Compute Unit(s) : NPU (871 ops)
121
  ```
122
 
123
 
 
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 | ONNX | 220.321 ms | 0 - 478 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
39
+ | HuggingFace-WavLM-Base-Plus | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 178.518 ms | 0 - 486 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 167.953 ms | 2 - 510 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
41
+ | HuggingFace-WavLM-Base-Plus | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 253.745 ms | 200 - 200 MB | FP16 | NPU | [HuggingFace-WavLM-Base-Plus.onnx](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.onnx) |
 
 
 
 
 
 
 
 
 
 
 
 
42
 
43
 
44
 
 
101
  ------------------------------------------------------------
102
  HuggingFace-WavLM-Base-Plus
103
  Device : Samsung Galaxy S23 (13)
104
+ Runtime : ONNX
105
+ Estimated inference time (ms) : 220.3
106
+ Estimated peak memory usage (MB): [0, 478]
107
+ Total # Ops : 686
108
+ Compute Unit(s) : NPU (686 ops)
109
  ```
110
 
111