Hugging Face's logo

qualcomm
/
Whisper-Tiny-En

Automatic Speech Recognition
PyTorch
TF Lite
foundation
android
Model card Files Community
qaihm-bot commited on
Commit
3e66184
•
1 Parent(s): 2358854

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +12 -10
README.md CHANGED
@@ -36,8 +36,10 @@ More details on model performance across various devices, can be found
36
 
37
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  | ---|---|---|---|---|---|---|---|
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 67.351 ms | 15 - 100 MB | FP16 | GPU | [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 7.115 ms | 3 - 5 MB | FP16 | NPU | [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite)
 
 
41
 
42
 
43
  ## Installation
@@ -98,17 +100,17 @@ python -m qai_hub_models.models.whisper_tiny_en.export
98
  ```
99
  Profile Job summary of WhisperEncoder
100
  --------------------------------------------------
101
- Device: QCS8550 (Proxy) (12)
102
- Estimated Inference Time: 67.31 ms
103
- Estimated Peak Memory Range: 16.33-60.40 MB
104
- Compute Units: GPU (209) | Total (209)
105
 
106
  Profile Job summary of WhisperDecoder
107
  --------------------------------------------------
108
- Device: QCS8550 (Proxy) (12)
109
- Estimated Inference Time: 7.15 ms
110
- Estimated Peak Memory Range: 2.84-5.14 MB
111
- Compute Units: NPU (303),CPU (2) | Total (305)
112
 
113
 
114
  ```
 
36
 
37
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  | ---|---|---|---|---|---|---|---|
39
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 68.887 ms | 11 - 54 MB | FP16 | GPU | [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite)
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.871 ms | 3 - 5 MB | FP16 | NPU | [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite)
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 288.969 ms | 0 - 52 MB | FP16 | NPU | [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 3.646 ms | 9 - 45 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so)
43
 
44
 
45
  ## Installation
 
100
  ```
101
  Profile Job summary of WhisperEncoder
102
  --------------------------------------------------
103
+ Device: Snapdragon X Elite CRD (11)
104
+ Estimated Inference Time: 240.12 ms
105
+ Estimated Peak Memory Range: 0.92-0.92 MB
106
+ Compute Units: NPU (337) | Total (337)
107
 
108
  Profile Job summary of WhisperDecoder
109
  --------------------------------------------------
110
+ Device: Snapdragon X Elite CRD (11)
111
+ Estimated Inference Time: 3.82 ms
112
+ Estimated Peak Memory Range: 20.25-20.25 MB
113
+ Compute Units: NPU (447) | Total (447)
114
 
115
 
116
  ```