qaihm-bot commited on
Commit
f320b34
·
verified ·
1 Parent(s): a1bf1de

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

Files changed (5) hide show
  1. .gitattributes +1 -0
  2. DEPLOYMENT_MODEL_LICENSE.pdf +3 -0
  3. LICENSE +2 -0
  4. README.md +4 -4
  5. YamNet.onnx +2 -2
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  YamNet.so filter=lfs diff=lfs merge=lfs -text
37
  YamNet.dlc filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  YamNet.so filter=lfs diff=lfs merge=lfs -text
37
  YamNet.dlc filter=lfs diff=lfs merge=lfs -text
38
+ DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
DEPLOYMENT_MODEL_LICENSE.pdf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
3
+ size 109629
LICENSE ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ The license of the original trained model can be found at https://github.com/w-hc/torch_audioset/blob/master/LICENSE.
2
+ The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -31,7 +31,7 @@ More details on model performance across various devices, can be found
31
  - Model checkpoint: yamnet.pth
32
  - Input resolution: 1x1x96x64
33
  - Number of parameters: 3.73M
34
- - Model size: 14.2 MB
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
@@ -55,13 +55,13 @@ More details on model performance across various devices, can be found
55
  | YamNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.352 ms | 0 - 14 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
56
  | YamNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.21 ms | 0 - 72 MB | NPU | [YamNet.tflite](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.tflite) |
57
  | YamNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.212 ms | 0 - 51 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
58
- | YamNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.29 ms | 0 - 24 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
59
  | YamNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.173 ms | 0 - 33 MB | NPU | [YamNet.tflite](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.tflite) |
60
  | YamNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.175 ms | 0 - 22 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
61
- | YamNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.234 ms | 0 - 23 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
62
  | YamNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.154 ms | 0 - 26 MB | NPU | [YamNet.tflite](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.tflite) |
63
  | YamNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.158 ms | 0 - 15 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
64
- | YamNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.252 ms | 0 - 15 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
65
  | YamNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.257 ms | 40 - 40 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
66
  | YamNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.269 ms | 8 - 8 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
67
 
 
31
  - Model checkpoint: yamnet.pth
32
  - Input resolution: 1x1x96x64
33
  - Number of parameters: 3.73M
34
+ - Model size (float): 14.2 MB
35
 
36
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
 
55
  | YamNet | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 0.352 ms | 0 - 14 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
56
  | YamNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 0.21 ms | 0 - 72 MB | NPU | [YamNet.tflite](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.tflite) |
57
  | YamNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 0.212 ms | 0 - 51 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
58
+ | YamNet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 0.291 ms | 0 - 27 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
59
  | YamNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 0.173 ms | 0 - 33 MB | NPU | [YamNet.tflite](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.tflite) |
60
  | YamNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 0.175 ms | 0 - 22 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
61
+ | YamNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 0.23 ms | 0 - 26 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
62
  | YamNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 0.154 ms | 0 - 26 MB | NPU | [YamNet.tflite](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.tflite) |
63
  | YamNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 0.158 ms | 0 - 15 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
64
+ | YamNet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 0.244 ms | 0 - 17 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
65
  | YamNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 0.257 ms | 40 - 40 MB | NPU | [YamNet.dlc](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.dlc) |
66
  | YamNet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.269 ms | 8 - 8 MB | NPU | [YamNet.onnx](https://huggingface.co/qualcomm/YamNet/blob/main/YamNet.onnx) |
67
 
YamNet.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97e095701a0d7849a087f7d6b70820f086eac2c353df3ca341722cfa2d5d16e5
3
- size 14935918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d2d300b4f8ed407aa3aa2a056f032942b157fa76a0732f0b46949fe8550f08
3
+ size 14938042