qaihm-bot commited on
Commit
e8901bf
·
verified ·
1 Parent(s): 42cbcfb

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -6
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 | 623.35 ms | 97 - 531 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 | 54.275 ms | 122 - 125 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 | 1890.126 ms | 0 - 243 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 | 11.949 ms | 61 - 128 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so)
45
 
46
 
47
 
@@ -104,14 +104,14 @@ python -m qai_hub_models.models.whisper_small_en.export
104
  Profile Job summary of WhisperEncoder
105
  --------------------------------------------------
106
  Device: Snapdragon X Elite CRD (11)
107
- Estimated Inference Time: 1087.18 ms
108
  Estimated Peak Memory Range: 0.46-0.46 MB
109
  Compute Units: NPU (1329) | Total (1329)
110
 
111
  Profile Job summary of WhisperDecoder
112
  --------------------------------------------------
113
  Device: Snapdragon X Elite CRD (11)
114
- Estimated Inference Time: 10.68 ms
115
  Estimated Peak Memory Range: 60.75-60.75 MB
116
  Compute Units: NPU (2255) | Total (2255)
117
 
 
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 | 620.742 ms | 0 - 415 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 | 25.837 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 | 1884.836 ms | 0 - 250 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 | 11.849 ms | 62 - 128 MB | FP16 | NPU | [WhisperDecoder.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so)
45
 
46
 
47
 
 
104
  Profile Job summary of WhisperEncoder
105
  --------------------------------------------------
106
  Device: Snapdragon X Elite CRD (11)
107
+ Estimated Inference Time: 1116.56 ms
108
  Estimated Peak Memory Range: 0.46-0.46 MB
109
  Compute Units: NPU (1329) | Total (1329)
110
 
111
  Profile Job summary of WhisperDecoder
112
  --------------------------------------------------
113
  Device: Snapdragon X Elite CRD (11)
114
+ Estimated Inference Time: 10.32 ms
115
  Estimated Peak Memory Range: 60.75-60.75 MB
116
  Compute Units: NPU (2255) | Total (2255)
117