Hugging Face's logo

STMicroelectronics
/
yamnet

Audio Classification
Model card Files
xet
Community
FBAGSTM commited on
Commit
c3255df
·
verified ·
1 Parent(s): 0a1a2dc

Update Readme ST Model Zoo

Browse files
Files changed (1) hide show
  1. README.md +8 -15
README.md CHANGED
@@ -1,7 +1,3 @@
1
- ---
2
- license: apache-2.0
3
- pipeline_tag: audio-classification
4
- ---
5
  # Quantized Yamnet
6
 
7
  ## **Use case** : `AED`
@@ -80,31 +76,30 @@ For Yamnet-1024
80
 
81
  * `tl` stands for "transfer learning", meaning that the model backbone weights were initialized from a pre-trained model, then only the last layer was unfrozen during the training.
82
 
83
-
84
  ### Reference **NPU** memory footprint based on ESC-10 dataset
85
  |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STM32Cube.AI version | STEdgeAI Core version |
86
  |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
87
- | [Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | esc-10 | Int8 | 64x96x1 | STM32N6 | 144 | 0.0 | 176.59 | 10.0.0 | 2.0.0 |
88
- | [Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10 | Int8 | 64x96x1 | STM32N6 | 144 | 0.0 | 3497.24 | 10.0.0 | 2.0.0 |
89
 
90
  ### Reference **NPU** inference time based on ESC-10 dataset
91
  | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
92
  |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
93
- | [Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | esc-10 | Int8 | 64x96x1 | STM32N6570-DK | NPU/MCU | 1.07 | 934.58 | 10.0.0 | 2.0.0 |
94
- | [Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10 | Int8 | 64x96x1 | STM32N6570-DK | NPU/MCU | 9.88 | 101.21 | 10.0.0 | 2.0.0 |
95
 
96
 
97
  ### Reference **MCU** memory footprint based on ESC-10 dataset
98
  | Model | Format | Resolution | Series | Activation RAM (kB) | Runtime RAM (kB) | Weights Flash (kB) | Code Flash (kB) | Total RAM (kB) | Total Flash (kB) | STM32Cube.AI version |
99
  |-------------------|--------|------------|---------|----------------|-------------|---------------|------------|-------------|-------------|-----------------------|
100
- |[Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A | 109.57 | 7.61 | 135.91 | 57.74 | 117.18 | 193.65 | 10.0.0 |
101
- |[Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 108.59 | 35.41 | 3162.66 | 334.30 | 144.0 | 3496.96 | 10.0.0 |
102
 
103
  ### Reference inference time based on ESC-10 dataset
104
  | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time | STM32Cube.AI version |
105
  |-------------------|--------|------------|------------------|------------------|--------------|-----------------|-----------------------|
106
- | [Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 281.95 ms | 10.0.0
107
- |[Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 1 CPU + 1 NPU | 800MhZ/1000MhZ | 11.949 ms | 10.0.0
108
 
109
 
110
  ### Accuracy with ESC-10 dataset
@@ -145,5 +140,3 @@ Note that accuracy with unknown class is lower. This is normal
145
 
146
  Please refer to the stm32ai-modelzoo-services GitHub [here](https://github.com/STMicroelectronics/stm32ai-modelzoo-services)
147
 
148
-
149
-
 
 
 
 
 
1
  # Quantized Yamnet
2
 
3
  ## **Use case** : `AED`
 
76
 
77
  * `tl` stands for "transfer learning", meaning that the model backbone weights were initialized from a pre-trained model, then only the last layer was unfrozen during the training.
78
 
 
79
  ### Reference **NPU** memory footprint based on ESC-10 dataset
80
  |Model | Dataset | Format | Resolution | Series | Internal RAM (KiB) | External RAM (KiB) | Weights Flash (KiB) | STM32Cube.AI version | STEdgeAI Core version |
81
  |----------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
82
+ | [Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | esc-10 | Int8 | 64x96x1 | STM32N6 | 144 | 0.0 | 167.7 | 10.2.0 | 2.2.0 |
83
+ | [Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10 | Int8 | 64x96x1 | STM32N6 | 144 | 0.0 | 3450.58 | 10.2.0 | 2.2.0 |
84
 
85
  ### Reference **NPU** inference time based on ESC-10 dataset
86
  | Model | Dataset | Format | Resolution | Board | Execution Engine | Inference time (ms) | Inf / sec | STM32Cube.AI version | STEdgeAI Core version |
87
  |--------|------------------|--------|-------------|------------------|------------------|---------------------|-------|----------------------|-------------------------|
88
+ | [Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | esc-10 | Int8 | 64x96x1 | STM32N6570-DK | NPU/MCU | 1.05 | 952.38 | 10.2.0 | 2.2.0 |
89
+ | [Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | esc-10 | Int8 | 64x96x1 | STM32N6570-DK | NPU/MCU | 9.88 | 101.21 | 10.2.0 | 2.2.0 |
90
 
91
 
92
  ### Reference **MCU** memory footprint based on ESC-10 dataset
93
  | Model | Format | Resolution | Series | Activation RAM (kB) | Runtime RAM (kB) | Weights Flash (kB) | Code Flash (kB) | Total RAM (kB) | Total Flash (kB) | STM32Cube.AI version |
94
  |-------------------|--------|------------|---------|----------------|-------------|---------------|------------|-------------|-------------|-----------------------|
95
+ |[Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A | 109.57 | 7.61 | 135.91 | 56.67 | 117.18 | 192.58 | 10.2.0 |
96
+ |[Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 144.0 | 1.67 | 3450.58 | 252.48 | 145.67 | 3703.06 | 10.2.0 |
97
 
98
  ### Reference inference time based on ESC-10 dataset
99
  | Model | Format | Resolution | Board | Execution Engine | Frequency | Inference time | STM32Cube.AI version |
100
  |-------------------|--------|------------|------------------|------------------|--------------|-----------------|-----------------------|
101
+ | [Yamnet 256](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_256_64x96_tl/yamnet_256_64x96_tl_int8.tflite) | Int8 | 64x96x1 | B-U585I-IOT02A | 1 CPU | 160 MHz | 279.62 ms | 10.2.0
102
+ |[Yamnet 1024](https://github.com/STMicroelectronics/stm32ai-modelzoo/tree/main/audio_event_detection/yamnet/ST_pretrainedmodel_public_dataset/esc10/yamnet_1024_64x96_tl/yamnet_1024_64x96_tl_qdq_int8.onnx) | Int8 | 64x96x1 | STM32N6 | 1 CPU + 1 NPU | 800MhZ/1000MhZ | 9.88 ms | 10.2.0
103
 
104
 
105
  ### Accuracy with ESC-10 dataset
 
140
 
141
  Please refer to the stm32ai-modelzoo-services GitHub [here](https://github.com/STMicroelectronics/stm32ai-modelzoo-services)
142