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
686e01d
·
verified ·
1 Parent(s): 6650758

v0.30.5

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

Files changed (1) hide show
  1. README.md +27 -14
README.md CHANGED
@@ -35,18 +35,31 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 2210.164 ms | 0 - 438 MB | 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 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 232.778 ms | 1 - 500 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 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 125.892 ms | 0 - 35 MB | 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 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 150.134 ms | 1 - 439 MB | NPU | [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 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 2210.164 ms | 0 - 438 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 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 126.995 ms | 0 - 39 MB | NPU | [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 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 251.498 ms | 1 - 498 MB | 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 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 125.894 ms | 0 - 34 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 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 150.134 ms | 1 - 439 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 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 127.466 ms | 0 - 37 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 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 88.295 ms | 0 - 446 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 83.675 ms | 1 - 441 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
 
 
 
 
 
 
 
 
 
 
 
 
 
50
 
51
 
52
 
@@ -110,8 +123,8 @@ Profiling Results
110
  HuggingFace-WavLM-Base-Plus
111
  Device : cs_8275 (ANDROID 14)
112
  Runtime : TFLITE
113
- Estimated inference time (ms) : 2210.2
114
- Estimated peak memory usage (MB): [0, 438]
115
  Total # Ops : 871
116
  Compute Unit(s) : npu (871 ops) gpu (0 ops) cpu (0 ops)
117
  ```
 
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | HuggingFace-WavLM-Base-Plus | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 2194.442 ms | 0 - 499 MB | 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 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 2379.893 ms | 1 - 10 MB | NPU | Use Export Script |
40
+ | HuggingFace-WavLM-Base-Plus | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 229.801 ms | 1 - 556 MB | 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 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 378.248 ms | 0 - 567 MB | NPU | Use Export Script |
42
+ | HuggingFace-WavLM-Base-Plus | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 119.018 ms | 0 - 37 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 | 231.856 ms | 0 - 3 MB | NPU | Use Export Script |
44
+ | HuggingFace-WavLM-Base-Plus | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 143.293 ms | 1 - 501 MB | 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 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 252.922 ms | 0 - 9 MB | NPU | Use Export Script |
46
+ | HuggingFace-WavLM-Base-Plus | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 2194.442 ms | 0 - 499 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 | 2379.893 ms | 1 - 10 MB | NPU | Use Export Script |
48
+ | HuggingFace-WavLM-Base-Plus | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 116.539 ms | 0 - 39 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 | 233.881 ms | 0 - 2 MB | NPU | Use Export Script |
50
+ | HuggingFace-WavLM-Base-Plus | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 250.196 ms | 1 - 549 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 | 315.496 ms | 0 - 17 MB | NPU | Use Export Script |
52
+ | HuggingFace-WavLM-Base-Plus | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 119.264 ms | 0 - 37 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 | 232.363 ms | 0 - 3 MB | NPU | Use Export Script |
54
+ | HuggingFace-WavLM-Base-Plus | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 143.293 ms | 1 - 501 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 | SA8775P ADP | Qualcomm® SA8775P | QNN | 252.922 ms | 0 - 9 MB | NPU | Use Export Script |
56
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 117.215 ms | 0 - 36 MB | NPU | [HuggingFace-WavLM-Base-Plus.tflite](https://huggingface.co/qualcomm/HuggingFace-WavLM-Base-Plus/blob/main/HuggingFace-WavLM-Base-Plus.tflite) |
57
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 232.148 ms | 0 - 41 MB | NPU | Use Export Script |
58
+ | HuggingFace-WavLM-Base-Plus | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 83.367 ms | 0 - 510 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 S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 170.09 ms | 0 - 567 MB | NPU | Use Export Script |
60
+ | HuggingFace-WavLM-Base-Plus | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 66.941 ms | 0 - 501 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 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 161.112 ms | 0 - 561 MB | NPU | Use Export Script |
62
+ | HuggingFace-WavLM-Base-Plus | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 232.834 ms | 0 - 0 MB | NPU | Use Export Script |
63
 
64
 
65
 
 
123
  HuggingFace-WavLM-Base-Plus
124
  Device : cs_8275 (ANDROID 14)
125
  Runtime : TFLITE
126
+ Estimated inference time (ms) : 2194.4
127
+ Estimated peak memory usage (MB): [0, 499]
128
  Total # Ops : 871
129
  Compute Unit(s) : npu (871 ops) gpu (0 ops) cpu (0 ops)
130
  ```