Hugging Face's logo

qualcomm
/
Whisper-Small-En

Automatic Speech Recognition
PyTorch
TF Lite
foundation
android
Model card Files Community
qaihm-bot commited on
Commit
41d9c90
•
1 Parent(s): 147d318

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -38,10 +38,10 @@ More details on model performance across various devices, can be found
38
 
39
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
40
  | ---|---|---|---|---|---|---|---|
41
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 615.85 ms | 53 - 482 MB | FP16 | GPU | [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite)
42
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 26.012 ms | 16 - 20 MB | FP16 | NPU | [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite)
43
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1802.215 ms | 0 - 225 MB | FP16 | NPU | [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.so)
44
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 24.923 ms | 115 - 186 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so)
45
 
46
 
47
 
@@ -103,16 +103,16 @@ python -m qai_hub_models.models.whisper_small_en.export
103
  ```
104
  Profile Job summary of WhisperEncoder
105
  --------------------------------------------------
106
- Device: Snapdragon X Elite CRD (11)
107
- Estimated Inference Time: 1093.55 ms
108
- Estimated Peak Memory Range: 0.92-0.92 MB
109
- Compute Units: NPU (1473) | Total (1473)
110
 
111
  Profile Job summary of WhisperDecoder
112
  --------------------------------------------------
113
  Device: SA8255 (Proxy) (13)
114
- Estimated Inference Time: 25.12 ms
115
- Estimated Peak Memory Range: 121.32-187.94 MB
116
  Compute Units: NPU (2255) | Total (2255)
117
 
118
 
 
38
 
39
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
40
  | ---|---|---|---|---|---|---|---|
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 608.885 ms | 80 - 511 MB | FP16 | GPU | [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 25.793 ms | 16 - 19 MB | FP16 | NPU | [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite)
43
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1873.577 ms | 0 - 226 MB | FP16 | NPU | [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.so)
44
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 12.151 ms | 61 - 130 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so)
45
 
46
 
47
 
 
103
  ```
104
  Profile Job summary of WhisperEncoder
105
  --------------------------------------------------
106
+ Device: SA8255 (Proxy) (13)
107
+ Estimated Inference Time: 1882.60 ms
108
+ Estimated Peak Memory Range: 0.52-223.35 MB
109
+ Compute Units: NPU (1329) | Total (1329)
110
 
111
  Profile Job summary of WhisperDecoder
112
  --------------------------------------------------
113
  Device: SA8255 (Proxy) (13)
114
+ Estimated Inference Time: 11.79 ms
115
+ Estimated Peak Memory Range: 60.69-127.91 MB
116
  Compute Units: NPU (2255) | Total (2255)
117
 
118