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
054c7c5
·
verified ·
1 Parent(s): 27b5840

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +11 -10
README.md CHANGED
@@ -35,14 +35,15 @@ 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 | 817.718 ms | 63 - 65 MB | FP32 | CPU | [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 S24 | Snapdragon® 8 Gen 3 | TFLITE | 631.561 ms | 63 - 84 MB | FP32 | 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 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 849.395 ms | 58 - 602 MB | FP32 | 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 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 850.762 ms | 63 - 65 MB | FP32 | 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 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 846.763 ms | 63 - 65 MB | FP32 | CPU | [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 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 889.799 ms | 63 - 66 MB | FP32 | 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 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1305.119 ms | 63 - 89 MB | FP32 | 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 568.662 ms | 63 - 78 MB | FP32 | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 
46
 
47
 
48
 
@@ -107,8 +108,8 @@ Profiling Results
107
  HuggingFace-WavLM-Base-Plus
108
  Device : Samsung Galaxy S23 (13)
109
  Runtime : TFLITE
110
- Estimated inference time (ms) : 817.7
111
- Estimated peak memory usage (MB): [63, 65]
112
  Total # Ops : 871
113
  Compute Unit(s) : CPU (871 ops)
114
  ```
 
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 | 955.105 ms | 63 - 66 MB | FP32 | CPU | [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 S24 | Snapdragon® 8 Gen 3 | TFLITE | 710.274 ms | 109 - 129 MB | FP32 | 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 534.137 ms | 61 - 75 MB | FP32 | 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 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 766.097 ms | 63 - 66 MB | FP32 | 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 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 855.844 ms | 63 - 100 MB | FP32 | CPU | [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 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 741.806 ms | 63 - 101 MB | FP32 | 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 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 791.448 ms | 31 - 55 MB | FP32 | 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 | SA8295P ADP | SA8295P | TFLITE | 1022.929 ms | 63 - 81 MB | FP32 | 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 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1188.577 ms | 63 - 87 MB | FP32 | CPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
47
 
48
 
49
 
 
108
  HuggingFace-WavLM-Base-Plus
109
  Device : Samsung Galaxy S23 (13)
110
  Runtime : TFLITE
111
+ Estimated inference time (ms) : 955.1
112
+ Estimated peak memory usage (MB): [63, 66]
113
  Total # Ops : 871
114
  Compute Unit(s) : CPU (871 ops)
115
  ```