Hugging Face's logo

qualcomm
/
HuggingFace-WavLM-Base-Plus

Automatic Speech Recognition
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
b085a6e
·
verified ·
1 Parent(s): f4f52a9

v0.47.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.

Files changed (1) hide show
  1. README.md +11 -18
README.md CHANGED
@@ -28,8 +28,7 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/huggingface_wavlm_base_plus/releases/v0.46.0/huggingface_wavlm_base_plus-onnx-float.zip)
32
- | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/huggingface_wavlm_base_plus/releases/v0.46.0/huggingface_wavlm_base_plus-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[HuggingFace-WavLM-Base-Plus on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/huggingface_wavlm_base_plus)**.
35
 
@@ -58,22 +57,16 @@ See our repository for [HuggingFace-WavLM-Base-Plus on GitHub](https://github.co
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
- | HuggingFace-WavLM-Base-Plus | ONNX | float | Snapdragon® X Elite | 295.294 ms | 202 - 202 MB | NPU
62
- | HuggingFace-WavLM-Base-Plus | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 219.292 ms | 1 - 1404 MB | NPU
63
- | HuggingFace-WavLM-Base-Plus | ONNX | float | Qualcomm® QCS8550 (Proxy) | 287.875 ms | 1 - 4 MB | NPU
64
- | HuggingFace-WavLM-Base-Plus | ONNX | float | Qualcomm® QCS9075 | 280.599 ms | 1 - 4 MB | NPU
65
- | HuggingFace-WavLM-Base-Plus | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 188.641 ms | 1 - 1006 MB | NPU
66
- | HuggingFace-WavLM-Base-Plus | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 154.394 ms | 1 - 1057 MB | NPU
67
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1421.172 ms | 117 - 1306 MB | CPU
68
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 2905.625 ms | 125 - 1049 MB | CPU
69
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1557.459 ms | 127 - 756 MB | CPU
70
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® SA8775P | 2260.664 ms | 125 - 1048 MB | CPU
71
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS9075 | 2287.921 ms | 125 - 710 MB | CPU
72
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2070.43 ms | 0 - 1289 MB | CPU
73
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® SA7255P | 2905.625 ms | 125 - 1049 MB | CPU
74
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® SA8295P | 1998.746 ms | 125 - 1108 MB | CPU
75
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1051.778 ms | 32 - 771 MB | CPU
76
- | HuggingFace-WavLM-Base-Plus | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 907.495 ms | 124 - 1277 MB | CPU
77
 
78
  ## License
79
  * The license for the original implementation of HuggingFace-WavLM-Base-Plus can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/huggingface_wavlm_base_plus/releases/v0.47.0/huggingface_wavlm_base_plus-tflite-float.zip)
 
32
 
33
  For more device-specific assets and performance metrics, visit **[HuggingFace-WavLM-Base-Plus on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/huggingface_wavlm_base_plus)**.
34
 
 
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1304.665 ms | 97 - 1289 MB | CPU
61
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 2918.323 ms | 125 - 1046 MB | CPU
62
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1600.414 ms | 125 - 194 MB | CPU
63
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® SA8775P | 2673.493 ms | 125 - 1047 MB | CPU
64
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS9075 | 2280.231 ms | 125 - 710 MB | CPU
65
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2142.178 ms | 125 - 1413 MB | CPU
66
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® SA7255P | 2918.323 ms | 125 - 1046 MB | CPU
67
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Qualcomm® SA8295P | 1986.309 ms | 125 - 1106 MB | CPU
68
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1108.187 ms | 125 - 872 MB | CPU
69
+ | HuggingFace-WavLM-Base-Plus | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 904.285 ms | 125 - 1275 MB | CPU
 
 
 
 
 
 
70
 
71
  ## License
72
  * The license for the original implementation of HuggingFace-WavLM-Base-Plus can be found