Hugging Face's logo

qualcomm
/
Whisper-Tiny-En

Automatic Speech Recognition
PyTorch
TF Lite
foundation
android
Model card Files Community
shreyajn commited on
Commit
2d18937
•
1 Parent(s): 22db323

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 | 68.595 ms | 18 - 64 MB | FP16 | GPU | [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite)
42
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 3.932 ms | 3 - 6 MB | FP16 | NPU | [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite)
43
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 276.902 ms | 0 - 50 MB | FP16 | NPU | [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so)
44
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.194 ms | 1 - 154 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so)
45
 
46
 
47
 
@@ -103,16 +103,16 @@ python -m qai_hub_models.models.whisper_tiny_en.export
103
  ```
104
  Profile Job summary of WhisperEncoder
105
  --------------------------------------------------
106
- Device: SA8255 (Proxy) (13)
107
- Estimated Inference Time: 278.96 ms
108
- Estimated Peak Memory Range: 0.16-50.72 MB
109
  Compute Units: NPU (313) | Total (313)
110
 
111
  Profile Job summary of WhisperDecoder
112
  --------------------------------------------------
113
- Device: SA8255 (Proxy) (13)
114
- Estimated Inference Time: 2.21 ms
115
- Estimated Peak Memory Range: 0.02-152.14 MB
116
  Compute Units: NPU (447) | Total (447)
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 | 70.794 ms | 0 - 123 MB | FP16 | GPU | [WhisperEncoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 10.44 ms | 21 - 28 MB | FP16 | NPU | [WhisperDecoder.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite)
43
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 277.614 ms | 0 - 43 MB | FP16 | NPU | [WhisperEncoder.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so)
44
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.237 ms | 0 - 133 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so)
45
 
46
 
47
 
 
103
  ```
104
  Profile Job summary of WhisperEncoder
105
  --------------------------------------------------
106
+ Device: Snapdragon X Elite CRD (11)
107
+ Estimated Inference Time: 239.74 ms
108
+ Estimated Peak Memory Range: 0.47-0.47 MB
109
  Compute Units: NPU (313) | Total (313)
110
 
111
  Profile Job summary of WhisperDecoder
112
  --------------------------------------------------
113
+ Device: Snapdragon X Elite CRD (11)
114
+ Estimated Inference Time: 2.06 ms
115
+ Estimated Peak Memory Range: 10.14-10.14 MB
116
  Compute Units: NPU (447) | Total (447)
117
 
118