Hugging Face's logo

qualcomm
/
Whisper-Medium-En

Other
PyTorch
deprecated
Model card Files
xet
Community
qaihm-bot commited on
Commit
8babe88
·
verified ·
1 Parent(s): 058fc64

v0.31.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.31.0 for changelog.

Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -37,14 +37,14 @@ More details on model performance across various devices, can be found
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
- | WhisperEncoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1977.2 ms | 249 - 299 MB | GPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
41
- | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1668.191 ms | 209 - 459 MB | GPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
42
- | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1658.962 ms | 186 - 233 MB | GPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
43
- | WhisperEncoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1538.79 ms | 953 - 953 MB | NPU | [Whisper-Medium-En.onnx](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.onnx) |
44
- | WhisperDecoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 93.037 ms | 42 - 1250 MB | NPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
45
- | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 96.398 ms | 42 - 1592 MB | NPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
46
- | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 82.708 ms | 34 - 1372 MB | NPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
47
- | WhisperDecoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 64.32 ms | 566 - 566 MB | NPU | [Whisper-Medium-En.onnx](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.onnx) |
48
 
49
 
50
 
@@ -108,8 +108,8 @@ Profiling Results
108
  WhisperEncoderInf
109
  Device : cs_auto_makena_8295 (ANDROID 14)
110
  Runtime : TFLITE
111
- Estimated inference time (ms) : 1977.2
112
- Estimated peak memory usage (MB): [249, 299]
113
  Total # Ops : 1991
114
  Compute Unit(s) : npu (0 ops) gpu (1980 ops) cpu (11 ops)
115
 
@@ -117,7 +117,7 @@ Compute Unit(s) : npu (0 ops) gpu (1980 ops) cpu (11 ops)
117
  WhisperDecoderInf
118
  Device : cs_auto_makena_8295 (ANDROID 14)
119
  Runtime : TFLITE
120
- Estimated inference time (ms) : 93.0
121
  Estimated peak memory usage (MB): [42, 1250]
122
  Total # Ops : 6377
123
  Compute Unit(s) : npu (6377 ops) gpu (0 ops) cpu (0 ops)
 
37
 
38
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
39
  |---|---|---|---|---|---|---|---|---|
40
+ | WhisperEncoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 1969.856 ms | 201 - 251 MB | GPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
41
+ | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1720.841 ms | 60 - 308 MB | GPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
42
+ | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1509.053 ms | 229 - 275 MB | GPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
43
+ | WhisperEncoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1545.124 ms | 953 - 953 MB | NPU | [Whisper-Medium-En.onnx](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.onnx) |
44
+ | WhisperDecoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 92.152 ms | 42 - 1250 MB | NPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
45
+ | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 91.218 ms | 42 - 1597 MB | NPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
46
+ | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 80.416 ms | 43 - 1382 MB | NPU | [Whisper-Medium-En.tflite](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.tflite) |
47
+ | WhisperDecoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 66.789 ms | 566 - 566 MB | NPU | [Whisper-Medium-En.onnx](https://huggingface.co/qualcomm/Whisper-Medium-En/blob/main/Whisper-Medium-En.onnx) |
48
 
49
 
50
 
 
108
  WhisperEncoderInf
109
  Device : cs_auto_makena_8295 (ANDROID 14)
110
  Runtime : TFLITE
111
+ Estimated inference time (ms) : 1969.9
112
+ Estimated peak memory usage (MB): [201, 251]
113
  Total # Ops : 1991
114
  Compute Unit(s) : npu (0 ops) gpu (1980 ops) cpu (11 ops)
115
 
 
117
  WhisperDecoderInf
118
  Device : cs_auto_makena_8295 (ANDROID 14)
119
  Runtime : TFLITE
120
+ Estimated inference time (ms) : 92.2
121
  Estimated peak memory usage (MB): [42, 1250]
122
  Total # Ops : 6377
123
  Compute Unit(s) : npu (6377 ops) gpu (0 ops) cpu (0 ops)