bhushans commited on
Commit
09d69b8
·
verified ·
1 Parent(s): bd19ada

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +49 -44
README.md CHANGED
@@ -38,44 +38,48 @@ 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
- | WhisperEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 98.056 ms | 15 - 132 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
42
- | WhisperEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 141.405 ms | 0 - 51 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so) |
43
- | WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 76.661 ms | 18 - 47 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
44
- | WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 112.275 ms | 0 - 190 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so) |
45
- | WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 78.773 ms | 18 - 38 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
46
- | WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 101.227 ms | 0 - 194 MB | FP16 | NPU | Use Export Script |
47
- | WhisperEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 102.8 ms | 16 - 60 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
48
- | WhisperEncoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 102.554 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
49
- | WhisperEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 122.669 ms | 15 - 121 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
50
- | WhisperEncoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 104.998 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
51
- | WhisperEncoder | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 99.384 ms | 18 - 130 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
52
- | WhisperEncoder | SA8775 (Proxy) | SA8775P Proxy | QNN | 106.066 ms | 0 - 11 MB | FP16 | NPU | Use Export Script |
53
- | WhisperEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 101.119 ms | 15 - 62 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
54
- | WhisperEncoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 104.287 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
55
- | WhisperEncoder | SA8295P ADP | SA8295P | TFLITE | 104.321 ms | 20 - 40 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
56
- | WhisperEncoder | SA8295P ADP | SA8295P | QNN | 127.364 ms | 1 - 6 MB | FP16 | NPU | Use Export Script |
57
- | WhisperEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 155.23 ms | 20 - 56 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
58
- | WhisperEncoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 162.925 ms | 0 - 197 MB | FP16 | NPU | Use Export Script |
59
- | WhisperEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 95.469 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
60
- | WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.304 ms | 3 - 5 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
61
- | WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.254 ms | 2 - 153 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so) |
62
- | WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.841 ms | 1 - 221 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
63
- | WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.652 ms | 4 - 25 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so) |
64
- | WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.482 ms | 0 - 31 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
65
- | WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.524 ms | 4 - 28 MB | FP16 | NPU | Use Export Script |
66
- | WhisperDecoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.771 ms | 3 - 5 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
67
- | WhisperDecoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.363 ms | 5 - 6 MB | FP16 | NPU | Use Export Script |
68
- | WhisperDecoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.667 ms | 3 - 5 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
69
- | WhisperDecoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.217 ms | 4 - 6 MB | FP16 | NPU | Use Export Script |
70
- | WhisperDecoder | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 3.725 ms | 3 - 6 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
71
- | WhisperDecoder | SA8775 (Proxy) | SA8775P Proxy | QNN | 2.262 ms | 9 - 12 MB | FP16 | NPU | Use Export Script |
72
- | WhisperDecoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.68 ms | 3 - 5 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
73
- | WhisperDecoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.266 ms | 3 - 4 MB | FP16 | NPU | Use Export Script |
74
  | WhisperDecoder | SA8295P ADP | SA8295P | TFLITE | 4.786 ms | 3 - 29 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
75
- | WhisperDecoder | SA8295P ADP | SA8295P | QNN | 3.334 ms | 9 - 15 MB | FP16 | NPU | Use Export Script |
76
- | WhisperDecoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.332 ms | 3 - 217 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
77
- | WhisperDecoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.71 ms | 4 - 28 MB | FP16 | NPU | Use Export Script |
78
- | WhisperDecoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.097 ms | 10 - 10 MB | FP16 | NPU | Use Export Script |
 
 
 
 
79
 
80
 
81
 
@@ -140,8 +144,8 @@ Profiling Results
140
  WhisperEncoder
141
  Device : Samsung Galaxy S23 (13)
142
  Runtime : TFLITE
143
- Estimated inference time (ms) : 98.1
144
- Estimated peak memory usage (MB): [15, 132]
145
  Total # Ops : 271
146
  Compute Unit(s) : GPU (260 ops) CPU (11 ops)
147
 
@@ -149,8 +153,8 @@ Compute Unit(s) : GPU (260 ops) CPU (11 ops)
149
  WhisperDecoder
150
  Device : Samsung Galaxy S23 (13)
151
  Runtime : TFLITE
152
- Estimated inference time (ms) : 4.3
153
- Estimated peak memory usage (MB): [3, 5]
154
  Total # Ops : 557
155
  Compute Unit(s) : NPU (557 ops)
156
  ```
@@ -171,11 +175,12 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
171
  import torch
172
 
173
  import qai_hub as hub
174
- from qai_hub_models.models.whisper_tiny_en import WhisperEncoder,WhisperDecoder
175
 
176
  # Load the model
177
- encoder_model = WhisperEncoder.from_pretrained()
178
- decoder_model = WhisperDecoder.from_pretrained()
 
179
 
180
  # Device
181
  device = hub.Device("Samsung Galaxy S23")
 
38
 
39
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
40
  |---|---|---|---|---|---|---|---|---|
41
+ | WhisperEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 102.517 ms | 15 - 102 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
42
+ | WhisperEncoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 140.918 ms | 0 - 52 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so) |
43
+ | WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 79.931 ms | 20 - 49 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
44
+ | WhisperEncoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 110.457 ms | 0 - 190 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.so) |
45
+ | WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 65.236 ms | 20 - 39 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
46
+ | WhisperEncoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 89.706 ms | 0 - 194 MB | FP16 | NPU | Use Export Script |
47
+ | WhisperEncoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 100.71 ms | 20 - 109 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
48
+ | WhisperEncoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 104.587 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
49
+ | WhisperEncoder | SA7255P ADP | SA7255P | TFLITE | 532.945 ms | 20 - 44 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
50
+ | WhisperEncoder | SA7255P ADP | SA7255P | QNN | 466.605 ms | 2 - 7 MB | FP16 | NPU | Use Export Script |
51
+ | WhisperEncoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 102.188 ms | 20 - 117 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
52
+ | WhisperEncoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 108.187 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
53
+ | WhisperEncoder | SA8295P ADP | SA8295P | TFLITE | 107.711 ms | 20 - 41 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
54
+ | WhisperEncoder | SA8295P ADP | SA8295P | QNN | 128.097 ms | 1 - 6 MB | FP16 | NPU | Use Export Script |
55
+ | WhisperEncoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 99.594 ms | 20 - 58 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
56
+ | WhisperEncoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 107.074 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
57
+ | WhisperEncoder | SA8775P ADP | SA8775P | TFLITE | 178.344 ms | 20 - 43 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
58
+ | WhisperEncoder | SA8775P ADP | SA8775P | QNN | 119.681 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
59
+ | WhisperEncoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 156.253 ms | 20 - 55 MB | FP16 | GPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperEncoder.tflite) |
60
+ | WhisperEncoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 158.505 ms | 0 - 194 MB | FP16 | NPU | Use Export Script |
61
+ | WhisperEncoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 97.524 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
62
+ | WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.993 ms | 3 - 50 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
63
+ | WhisperDecoder | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.409 ms | 0 - 80 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so) |
64
+ | WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.077 ms | 0 - 58 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
65
+ | WhisperDecoder | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.726 ms | 0 - 42 MB | FP16 | NPU | [Whisper-Tiny-En.so](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.so) |
66
+ | WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.624 ms | 2 - 57 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
67
+ | WhisperDecoder | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.421 ms | 10 - 50 MB | FP16 | NPU | Use Export Script |
68
+ | WhisperDecoder | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.056 ms | 3 - 41 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
69
+ | WhisperDecoder | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.377 ms | 5 - 7 MB | FP16 | NPU | Use Export Script |
70
+ | WhisperDecoder | SA7255P ADP | SA7255P | TFLITE | 18.142 ms | 3 - 56 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
71
+ | WhisperDecoder | SA7255P ADP | SA7255P | QNN | 15.519 ms | 9 - 15 MB | FP16 | NPU | Use Export Script |
72
+ | WhisperDecoder | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.952 ms | 2 - 41 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
73
+ | WhisperDecoder | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.333 ms | 2 - 4 MB | FP16 | NPU | Use Export Script |
74
  | WhisperDecoder | SA8295P ADP | SA8295P | TFLITE | 4.786 ms | 3 - 29 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
75
+ | WhisperDecoder | SA8295P ADP | SA8295P | QNN | 3.598 ms | 1 - 7 MB | FP16 | NPU | Use Export Script |
76
+ | WhisperDecoder | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.997 ms | 3 - 50 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
77
+ | WhisperDecoder | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.44 ms | 8 - 10 MB | FP16 | NPU | Use Export Script |
78
+ | WhisperDecoder | SA8775P ADP | SA8775P | TFLITE | 5.308 ms | 3 - 57 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
79
+ | WhisperDecoder | SA8775P ADP | SA8775P | QNN | 3.448 ms | 9 - 14 MB | FP16 | NPU | Use Export Script |
80
+ | WhisperDecoder | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.622 ms | 3 - 59 MB | FP16 | NPU | [Whisper-Tiny-En.tflite](https://huggingface.co/qualcomm/Whisper-Tiny-En/blob/main/WhisperDecoder.tflite) |
81
+ | WhisperDecoder | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.923 ms | 9 - 51 MB | FP16 | NPU | Use Export Script |
82
+ | WhisperDecoder | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.29 ms | 10 - 10 MB | FP16 | NPU | Use Export Script |
83
 
84
 
85
 
 
144
  WhisperEncoder
145
  Device : Samsung Galaxy S23 (13)
146
  Runtime : TFLITE
147
+ Estimated inference time (ms) : 102.5
148
+ Estimated peak memory usage (MB): [15, 102]
149
  Total # Ops : 271
150
  Compute Unit(s) : GPU (260 ops) CPU (11 ops)
151
 
 
153
  WhisperDecoder
154
  Device : Samsung Galaxy S23 (13)
155
  Runtime : TFLITE
156
+ Estimated inference time (ms) : 4.0
157
+ Estimated peak memory usage (MB): [3, 50]
158
  Total # Ops : 557
159
  Compute Unit(s) : NPU (557 ops)
160
  ```
 
175
  import torch
176
 
177
  import qai_hub as hub
178
+ from qai_hub_models.models.whisper_tiny_en import Model
179
 
180
  # Load the model
181
+ model = Model.from_pretrained()
182
+ encoder_model = model.encoder
183
+ decoder_model = model.decoder
184
 
185
  # Device
186
  device = hub.Device("Samsung Galaxy S23")