Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -38,46 +38,54 @@ More details on model performance across various devices, can be found
|
|
38 |
|
39 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
|---|---|---|---|---|---|---|---|---|
|
41 |
-
| WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 29.
|
42 |
-
| WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 11.
|
43 |
-
| WhisperDecoder | Samsung Galaxy
|
44 |
-
| WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 |
|
45 |
-
| WhisperDecoder |
|
46 |
-
| WhisperDecoder |
|
47 |
-
| WhisperDecoder |
|
48 |
-
| WhisperDecoder |
|
49 |
-
| WhisperDecoder |
|
50 |
-
| WhisperDecoder |
|
51 |
-
| WhisperDecoder |
|
52 |
-
| WhisperDecoder |
|
53 |
-
| WhisperDecoder |
|
54 |
-
| WhisperDecoder |
|
55 |
-
| WhisperDecoder |
|
56 |
-
| WhisperDecoder |
|
57 |
-
| WhisperDecoder |
|
58 |
-
| WhisperDecoder |
|
59 |
-
| WhisperDecoder |
|
60 |
-
| WhisperDecoder |
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
|
|
65 |
-
|
|
66 |
-
| WhisperEncoder |
|
67 |
-
| WhisperEncoder |
|
68 |
-
| WhisperEncoder |
|
69 |
-
| WhisperEncoder |
|
70 |
-
| WhisperEncoder |
|
71 |
-
| WhisperEncoder |
|
72 |
-
| WhisperEncoder |
|
73 |
-
| WhisperEncoder |
|
74 |
-
| WhisperEncoder |
|
75 |
-
| WhisperEncoder |
|
76 |
-
| WhisperEncoder |
|
77 |
-
| WhisperEncoder |
|
78 |
-
| WhisperEncoder |
|
79 |
-
| WhisperEncoder |
|
80 |
-
| WhisperEncoder |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
|
82 |
|
83 |
|
@@ -142,8 +150,8 @@ Profiling Results
|
|
142 |
WhisperDecoder
|
143 |
Device : Samsung Galaxy S23 (13)
|
144 |
Runtime : TFLITE
|
145 |
-
Estimated inference time (ms) : 29.
|
146 |
-
Estimated peak memory usage (MB): [
|
147 |
Total # Ops : 2573
|
148 |
Compute Unit(s) : NPU (2573 ops)
|
149 |
|
@@ -151,8 +159,8 @@ Compute Unit(s) : NPU (2573 ops)
|
|
151 |
WhisperEncoder
|
152 |
Device : Samsung Galaxy S23 (13)
|
153 |
Runtime : TFLITE
|
154 |
-
Estimated inference time (ms) :
|
155 |
-
Estimated peak memory usage (MB): [
|
156 |
Total # Ops : 911
|
157 |
Compute Unit(s) : GPU (900 ops) CPU (11 ops)
|
158 |
```
|
|
|
38 |
|
39 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
|---|---|---|---|---|---|---|---|---|
|
41 |
+
| WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 29.126 ms | 16 - 96 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
42 |
+
| WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 11.961 ms | 54 - 137 MB | FP16 | NPU | [Whisper-Small-En.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so) |
|
43 |
+
| WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 61.425 ms | 154 - 199 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.onnx) |
|
44 |
+
| WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 23.441 ms | 16 - 150 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
45 |
+
| WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 9.604 ms | 53 - 160 MB | FP16 | NPU | [Whisper-Small-En.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.so) |
|
46 |
+
| WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 51.698 ms | 16 - 327 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.onnx) |
|
47 |
+
| WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 18.162 ms | 16 - 176 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
48 |
+
| WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 7.555 ms | 49 - 184 MB | FP16 | NPU | Use Export Script |
|
49 |
+
| WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 42.696 ms | 86 - 408 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.onnx) |
|
50 |
+
| WhisperDecoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 29.309 ms | 16 - 101 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
51 |
+
| WhisperDecoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 12.213 ms | 61 - 63 MB | FP16 | NPU | Use Export Script |
|
52 |
+
| WhisperDecoder | SA7255P ADP | SA7255P | TFLITE | 100.26 ms | 16 - 175 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
53 |
+
| WhisperDecoder | SA7255P ADP | SA7255P | QNN | 74.87 ms | 60 - 70 MB | FP16 | NPU | Use Export Script |
|
54 |
+
| WhisperDecoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 29.902 ms | 16 - 101 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
55 |
+
| WhisperDecoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 12.096 ms | 54 - 55 MB | FP16 | NPU | Use Export Script |
|
56 |
+
| WhisperDecoder | SA8295P ADP | SA8295P | TFLITE | 31.128 ms | 16 - 164 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
57 |
+
| WhisperDecoder | SA8295P ADP | SA8295P | QNN | 14.544 ms | 57 - 71 MB | FP16 | NPU | Use Export Script |
|
58 |
+
| WhisperDecoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 29.982 ms | 14 - 97 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
59 |
+
| WhisperDecoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 12.14 ms | 57 - 59 MB | FP16 | NPU | Use Export Script |
|
60 |
+
| WhisperDecoder | SA8775P ADP | SA8775P | TFLITE | 33.024 ms | 16 - 175 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
61 |
+
| WhisperDecoder | SA8775P ADP | SA8775P | QNN | 14.735 ms | 57 - 66 MB | FP16 | NPU | Use Export Script |
|
62 |
+
| WhisperDecoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 33.055 ms | 16 - 140 MB | FP16 | NPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.tflite) |
|
63 |
+
| WhisperDecoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 16.795 ms | 53 - 172 MB | FP16 | NPU | Use Export Script |
|
64 |
+
| WhisperDecoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 10.56 ms | 61 - 61 MB | FP16 | NPU | Use Export Script |
|
65 |
+
| WhisperDecoder | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 52.337 ms | 232 - 232 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperDecoder.onnx) |
|
66 |
+
| WhisperEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 807.519 ms | 79 - 160 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
67 |
+
| WhisperEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 804.747 ms | 0 - 211 MB | FP16 | NPU | [Whisper-Small-En.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.so) |
|
68 |
+
| WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 602.309 ms | 110 - 200 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
69 |
+
| WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 597.586 ms | 0 - 837 MB | FP16 | NPU | [Whisper-Small-En.so](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.so) |
|
70 |
+
| WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 869.225 ms | 0 - 1429 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.onnx) |
|
71 |
+
| WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 544.489 ms | 111 - 141 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
72 |
+
| WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 515.742 ms | 0 - 906 MB | FP16 | NPU | Use Export Script |
|
73 |
+
| WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 677.156 ms | 172 - 1609 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.onnx) |
|
74 |
+
| WhisperEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1255.513 ms | 18 - 221 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
75 |
+
| WhisperEncoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 675.441 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
76 |
+
| WhisperEncoder | SA7255P ADP | SA7255P | TFLITE | 4429.057 ms | 109 - 142 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
77 |
+
| WhisperEncoder | SA7255P ADP | SA7255P | QNN | 3217.361 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
|
78 |
+
| WhisperEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 685.501 ms | 110 - 158 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
79 |
+
| WhisperEncoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 687.338 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
|
80 |
+
| WhisperEncoder | SA8295P ADP | SA8295P | TFLITE | 657.369 ms | 110 - 142 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
81 |
+
| WhisperEncoder | SA8295P ADP | SA8295P | QNN | 700.793 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
|
82 |
+
| WhisperEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 686.08 ms | 50 - 129 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
83 |
+
| WhisperEncoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 674.708 ms | 0 - 3 MB | FP16 | NPU | Use Export Script |
|
84 |
+
| WhisperEncoder | SA8775P ADP | SA8775P | TFLITE | 1287.541 ms | 88 - 121 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
85 |
+
| WhisperEncoder | SA8775P ADP | SA8775P | QNN | 604.581 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
|
86 |
+
| WhisperEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 983.989 ms | 58 - 157 MB | FP16 | GPU | [Whisper-Small-En.tflite](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.tflite) |
|
87 |
+
| WhisperEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 505.395 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
|
88 |
+
| WhisperEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1340.942 ms | 237 - 237 MB | FP16 | NPU | [Whisper-Small-En.onnx](https://huggingface.co/qualcomm/Whisper-Small-En/blob/main/WhisperEncoder.onnx) |
|
89 |
|
90 |
|
91 |
|
|
|
150 |
WhisperDecoder
|
151 |
Device : Samsung Galaxy S23 (13)
|
152 |
Runtime : TFLITE
|
153 |
+
Estimated inference time (ms) : 29.1
|
154 |
+
Estimated peak memory usage (MB): [16, 96]
|
155 |
Total # Ops : 2573
|
156 |
Compute Unit(s) : NPU (2573 ops)
|
157 |
|
|
|
159 |
WhisperEncoder
|
160 |
Device : Samsung Galaxy S23 (13)
|
161 |
Runtime : TFLITE
|
162 |
+
Estimated inference time (ms) : 807.5
|
163 |
+
Estimated peak memory usage (MB): [79, 160]
|
164 |
Total # Ops : 911
|
165 |
Compute Unit(s) : GPU (900 ops) CPU (11 ops)
|
166 |
```
|