Hugging Face's logo

qualcomm
/
Whisper-Base-En

Other
PyTorch
deprecated
Model card Files
xet
Community
1
qaihm-bot commited on
Commit
8b776d7
·
verified ·
1 Parent(s): d6d71e0

v0.35.0

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.35.0 for changelog.

Files changed (16) hide show
  1. .gitattributes +2 -0
  2. LICENSE +1 -1
  3. README.md +61 -67
  4. Whisper-Base-En_WhisperDecoderInf.dlc → Whisper-Base-En_HfWhisperDecoder.dlc +2 -2
  5. Whisper-Base-En_WhisperDecoderInf.onnx.zip → Whisper-Base-En_HfWhisperDecoder.tflite +2 -2
  6. Whisper-Base-En_WhisperEncoderInf.onnx.zip → Whisper-Base-En_HfWhisperEncoder.dlc +2 -2
  7. Whisper-Base-En_WhisperEncoderInf.tflite → Whisper-Base-En_HfWhisperEncoder.tflite +2 -2
  8. Whisper-Base-En_WhisperDecoderInf.tflite → precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_HfWhisperDecoder.bin +2 -2
  9. precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_HfWhisperDecoder.onnx.zip +3 -0
  10. precompiled/qualcomm-snapdragon-x-elite/{Whisper-Base-En_WhisperEncoderInf.bin → Whisper-Base-En_HfWhisperEncoder.bin} +2 -2
  11. Whisper-Base-En_WhisperEncoderInf.dlc → precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_HfWhisperEncoder.onnx.zip +2 -2
  12. precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_WhisperDecoderInf.bin +0 -3
  13. precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_WhisperDecoderInf.onnx.zip +0 -3
  14. precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_WhisperEncoderInf.onnx.zip +0 -3
  15. precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml +1 -1
  16. sdk_versions.yml +5 -0
.gitattributes CHANGED
@@ -40,3 +40,5 @@ WhisperDecoderInf.so filter=lfs diff=lfs merge=lfs -text
40
  Whisper-Base-En_WhisperDecoderInf.dlc filter=lfs diff=lfs merge=lfs -text
41
  Whisper-Base-En_WhisperEncoderInf.dlc filter=lfs diff=lfs merge=lfs -text
42
  DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
 
 
 
40
  Whisper-Base-En_WhisperDecoderInf.dlc filter=lfs diff=lfs merge=lfs -text
41
  Whisper-Base-En_WhisperEncoderInf.dlc filter=lfs diff=lfs merge=lfs -text
42
  DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
43
+ Whisper-Base-En_HfWhisperDecoder.dlc filter=lfs diff=lfs merge=lfs -text
44
+ Whisper-Base-En_HfWhisperEncoder.dlc filter=lfs diff=lfs merge=lfs -text
LICENSE CHANGED
@@ -1,2 +1,2 @@
1
- The license of the original trained model can be found at https://github.com/openai/whisper/blob/main/LICENSE.
2
  The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
 
1
+ The license of the original trained model can be found at https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE.
2
  The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.
README.md CHANGED
@@ -11,12 +11,12 @@ pipeline_tag: automatic-speech-recognition
11
  ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base_en/web-assets/model_demo.png)
12
 
13
  # Whisper-Base-En: Optimized for Mobile Deployment
14
- ## Automatic speech recognition (ASR) model for English transcription as well as translation
15
 
16
 
17
- OpenAI’s Whisper ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text. It exhibits robust performance in realistic, noisy environments, making it highly reliable for real-world applications. Specifically, it excels in long-form transcription, capable of accurately transcribing audio clips up to 30 seconds long. Time to the first token is the encoder's latency, while time to each additional token is decoder's latency, where we assume a mean decoded length specified below.
18
 
19
- This model is an implementation of Whisper-Base-En found [here](https://github.com/openai/whisper/tree/main).
20
 
21
 
22
  This repository provides scripts to run Whisper-Base-En on Qualcomm® devices.
@@ -29,72 +29,66 @@ More details on model performance across various devices, can be found
29
 
30
  - **Model Type:** Model_use_case.speech_recognition
31
  - **Model Stats:**
32
- - Model checkpoint: base.en
33
  - Input resolution: 80x3000 (30 seconds audio)
34
- - Mean decoded sequence length: 112 tokens
35
- - Number of parameters (WhisperEncoderInf): 23.7M
36
- - Model size (WhisperEncoderInf) (float): 90.6 MB
37
- - Number of parameters (WhisperDecoderInf): 48.8M
38
- - Model size (WhisperDecoderInf) (float): 186 MB
39
 
40
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
41
  |---|---|---|---|---|---|---|---|---|
42
- | WhisperEncoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 853.873 ms | 36 - 61 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
43
- | WhisperEncoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 315.193 ms | 1 - 1399 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
44
- | WhisperEncoderInf | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 275.493 ms | 38 - 87 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
45
- | WhisperEncoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 206.249 ms | 0 - 54 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
46
- | WhisperEncoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 205.831 ms | 0 - 358 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
47
- | WhisperEncoderInf | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 352.898 ms | 38 - 63 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
48
- | WhisperEncoderInf | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 204.363 ms | 0 - 1398 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
49
- | WhisperEncoderInf | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 853.873 ms | 36 - 61 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
50
- | WhisperEncoderInf | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 315.193 ms | 1 - 1399 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
51
- | WhisperEncoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 204.901 ms | 0 - 58 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
52
- | WhisperEncoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 167.203 ms | 0 - 355 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
53
- | WhisperEncoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 187.316 ms | 38 - 69 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
54
- | WhisperEncoderInf | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 217.911 ms | 1 - 1392 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
55
- | WhisperEncoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 202.667 ms | 0 - 75 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
56
- | WhisperEncoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 161.769 ms | 0 - 357 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
57
- | WhisperEncoderInf | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 352.898 ms | 38 - 63 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
58
- | WhisperEncoderInf | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 204.363 ms | 0 - 1398 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
59
- | WhisperEncoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 219.226 ms | 0 - 60 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
60
- | WhisperEncoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 218.463 ms | 0 - 355 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
61
- | WhisperEncoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 259.434 ms | 10 - 569 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
62
- | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 160.892 ms | 39 - 81 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
63
- | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 142.136 ms | 0 - 1370 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
64
- | WhisperEncoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 190.438 ms | 92 - 1646 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
65
- | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 133.952 ms | 37 - 66 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
66
- | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 115.265 ms | 1 - 1377 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
67
- | WhisperEncoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 150.849 ms | 90 - 1645 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
68
- | WhisperEncoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 162.983 ms | 136 - 136 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
69
- | WhisperEncoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 207.702 ms | 133 - 133 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
70
- | WhisperDecoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 16.58 ms | 0 - 134 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
71
- | WhisperDecoderInf | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.813 ms | 11 - 80 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
72
- | WhisperDecoderInf | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 10.663 ms | 5 - 136 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
73
- | WhisperDecoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 9.673 ms | 5 - 38 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
74
- | WhisperDecoderInf | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 4.071 ms | 20 - 47 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
75
- | WhisperDecoderInf | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 10.824 ms | 0 - 132 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
76
- | WhisperDecoderInf | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.864 ms | 19 - 83 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
77
- | WhisperDecoderInf | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 16.58 ms | 0 - 134 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
78
- | WhisperDecoderInf | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 6.813 ms | 11 - 80 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
79
- | WhisperDecoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 9.675 ms | 5 - 38 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
80
- | WhisperDecoderInf | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.071 ms | 20 - 46 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
81
- | WhisperDecoderInf | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 11.666 ms | 5 - 129 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
82
- | WhisperDecoderInf | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 5.223 ms | 11 - 70 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
83
- | WhisperDecoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 9.637 ms | 5 - 41 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
84
- | WhisperDecoderInf | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 4.036 ms | 20 - 45 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
85
- | WhisperDecoderInf | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 10.824 ms | 0 - 132 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
86
- | WhisperDecoderInf | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.864 ms | 19 - 83 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
87
- | WhisperDecoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 9.65 ms | 6 - 35 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
88
- | WhisperDecoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 4.062 ms | 20 - 43 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
89
- | WhisperDecoderInf | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 10.009 ms | 0 - 142 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
90
- | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 7.488 ms | 5 - 149 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
91
- | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.149 ms | 16 - 91 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
92
- | WhisperDecoderInf | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 8.306 ms | 56 - 183 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
93
- | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 7.381 ms | 4 - 133 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
94
- | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.704 ms | 19 - 90 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
95
- | WhisperDecoderInf | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 7.631 ms | 56 - 166 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
96
- | WhisperDecoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.752 ms | 231 - 231 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
97
- | WhisperDecoderInf | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.905 ms | 107 - 107 MB | NPU | [Whisper-Base-En.onnx](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.onnx) |
98
 
99
 
100
 
@@ -255,14 +249,14 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
255
 
256
  ## License
257
  * The license for the original implementation of Whisper-Base-En can be found
258
- [here](https://github.com/openai/whisper/blob/main/LICENSE).
259
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
260
 
261
 
262
 
263
  ## References
264
  * [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf)
265
- * [Source Model Implementation](https://github.com/openai/whisper/tree/main)
266
 
267
 
268
 
 
11
  ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base_en/web-assets/model_demo.png)
12
 
13
  # Whisper-Base-En: Optimized for Mobile Deployment
14
+ ## Transformer-based automatic speech recognition (ASR) model for multilingual transcription and translation available on HuggingFace
15
 
16
 
17
+ HuggingFace Whisper-Small ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text. This model is based on the transformer architecture and has been optimized for edge inference by replacing Multi-Head Attention (MHA) with Single-Head Attention (SHA) and linear layers with convolutional (conv) layers. It exhibits robust performance in realistic, noisy environments, making it highly reliable for real-world applications. Specifically, it excels in long-form transcription, capable of accurately transcribing audio clips up to 30 seconds long. Time to the first token is the encoder's latency, while time to each additional token is decoder's latency, where we assume a max decoded length specified below.
18
 
19
+ This model is an implementation of Whisper-Base-En found [here](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper).
20
 
21
 
22
  This repository provides scripts to run Whisper-Base-En on Qualcomm® devices.
 
29
 
30
  - **Model Type:** Model_use_case.speech_recognition
31
  - **Model Stats:**
32
+ - Model checkpoint: openai/whisper-base
33
  - Input resolution: 80x3000 (30 seconds audio)
34
+ - Max decoded sequence length: 200 tokens
35
+ - Number of parameters (HfWhisperEncoder): 23.7M
36
+ - Model size (HfWhisperEncoder) (float): 90.7 MB
37
+ - Number of parameters (HfWhisperDecoder): 48.9M
38
+ - Model size (HfWhisperDecoder) (float): 187 MB
39
 
40
  | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
41
  |---|---|---|---|---|---|---|---|---|
42
+ | HfWhisperEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 863.839 ms | 38 - 66 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
43
+ | HfWhisperEncoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 130.073 ms | 0 - 130 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
44
+ | HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 292.604 ms | 38 - 111 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
45
+ | HfWhisperEncoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 112.638 ms | 1 - 130 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
46
+ | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 234.299 ms | 0 - 69 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
47
+ | HfWhisperEncoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 43.537 ms | 0 - 45 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
48
+ | HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 400.795 ms | 38 - 67 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
49
+ | HfWhisperEncoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 50.197 ms | 1 - 133 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
50
+ | HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 863.839 ms | 38 - 66 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
51
+ | HfWhisperEncoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 130.073 ms | 0 - 130 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
52
+ | HfWhisperEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 257.222 ms | 0 - 71 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
53
+ | HfWhisperEncoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 43.566 ms | 0 - 43 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
54
+ | HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 229.608 ms | 38 - 74 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
55
+ | HfWhisperEncoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 92.405 ms | 0 - 139 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
56
+ | HfWhisperEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 229.942 ms | 0 - 68 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
57
+ | HfWhisperEncoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 43.746 ms | 0 - 42 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
58
+ | HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 400.795 ms | 38 - 67 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
59
+ | HfWhisperEncoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 50.197 ms | 1 - 133 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
60
+ | HfWhisperEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 230.509 ms | 38 - 114 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
61
+ | HfWhisperEncoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 43.232 ms | 1 - 41 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
62
+ | HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 174.142 ms | 38 - 105 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
63
+ | HfWhisperEncoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 34.16 ms | 0 - 135 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
64
+ | HfWhisperEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 171.96 ms | 37 - 67 MB | GPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
65
+ | HfWhisperEncoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 27.427 ms | 0 - 129 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
66
+ | HfWhisperEncoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 42.083 ms | 33 - 33 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
67
+ | HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 9.663 ms | 5 - 153 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
68
+ | HfWhisperDecoder | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 6.259 ms | 9 - 62 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
69
+ | HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 7.142 ms | 5 - 195 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
70
+ | HfWhisperDecoder | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 5.165 ms | 17 - 71 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
71
+ | HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 6.046 ms | 2 - 388 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
72
+ | HfWhisperDecoder | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 3.874 ms | 20 - 32 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
73
+ | HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.999 ms | 5 - 154 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
74
+ | HfWhisperDecoder | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 4.701 ms | 19 - 69 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
75
+ | HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 9.663 ms | 5 - 153 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
76
+ | HfWhisperDecoder | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 6.259 ms | 9 - 62 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
77
+ | HfWhisperDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 5.937 ms | 2 - 373 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
78
+ | HfWhisperDecoder | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 4.004 ms | 20 - 33 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
79
+ | HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 7.372 ms | 5 - 151 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
80
+ | HfWhisperDecoder | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 5.244 ms | 15 - 113 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
81
+ | HfWhisperDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 5.978 ms | 2 - 328 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
82
+ | HfWhisperDecoder | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 3.905 ms | 20 - 32 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
83
+ | HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 6.999 ms | 5 - 154 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
84
+ | HfWhisperDecoder | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 4.701 ms | 19 - 69 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
85
+ | HfWhisperDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.929 ms | 2 - 249 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
86
+ | HfWhisperDecoder | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 3.978 ms | 20 - 32 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
87
+ | HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.517 ms | 3 - 190 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
88
+ | HfWhisperDecoder | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.178 ms | 5 - 62 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
89
+ | HfWhisperDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 4.061 ms | 3 - 154 MB | NPU | [Whisper-Base-En.tflite](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.tflite) |
90
+ | HfWhisperDecoder | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 2.622 ms | 20 - 80 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
91
+ | HfWhisperDecoder | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 3.57 ms | 150 - 150 MB | NPU | [Whisper-Base-En.dlc](https://huggingface.co/qualcomm/Whisper-Base-En/blob/main/Whisper-Base-En.dlc) |
 
 
 
 
 
 
92
 
93
 
94
 
 
249
 
250
  ## License
251
  * The license for the original implementation of Whisper-Base-En can be found
252
+ [here](https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE).
253
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
254
 
255
 
256
 
257
  ## References
258
  * [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf)
259
+ * [Source Model Implementation](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper)
260
 
261
 
262
 
Whisper-Base-En_WhisperDecoderInf.dlc → Whisper-Base-En_HfWhisperDecoder.dlc RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2296cbdc00aeddbef9996a6ae61d7d99402abd50613231cb6b72c371648625ec
3
- size 151219841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f03c484b3c231c18119a99de98e578996956ae7cae44cc6d7f3f4585a77279
3
+ size 151746244
Whisper-Base-En_WhisperDecoderInf.onnx.zip → Whisper-Base-En_HfWhisperDecoder.tflite RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eabaab364b5754f91379e9aa8348f6aa06236960fd6f65fd42162a20a51b370
3
- size 186326975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a5b34879b6cbedb346e4fbc1cdaa3ea02ca258a38af2212292bf9c6079b10e
3
+ size 195855180
Whisper-Base-En_WhisperEncoderInf.onnx.zip → Whisper-Base-En_HfWhisperEncoder.dlc RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d56beca4c1f4b3342d32e9babed1738e5d09e870d2abce981cf3b1f46a1e08de
3
- size 59870431
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b12b75a1d235019930ee1657d9617c0d013f7de52b55a6a5df3c3e75172ccdf
3
+ size 48171764
Whisper-Base-En_WhisperEncoderInf.tflite → Whisper-Base-En_HfWhisperEncoder.tflite RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f08f676eaac9668af493748648b4aa63b6eba4b27abfabff9bc7a520c37ddb4
3
- size 95043000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a10aa2de61dbd3ebc33e5d1d3cd424724a8934d5fc03037fdee31787c2dd8c4
3
+ size 95114652
Whisper-Base-En_WhisperDecoderInf.tflite → precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_HfWhisperDecoder.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eeb09bbea9eb07e7b65b63ca1a81bb412745ab5ca678fa6bbdc9347db506bda
3
- size 195329400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9d5880d780756e56417aa6a23c1648e02cba2fd64e095ea86caa8ca0074e0f4
3
+ size 151846912
precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_HfWhisperDecoder.onnx.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69b6b09c3f1de637f764fd06cefaa9815414baeae648513f8bdf2b31f4c7aa9
3
+ size 137259306
precompiled/qualcomm-snapdragon-x-elite/{Whisper-Base-En_WhisperEncoderInf.bin → Whisper-Base-En_HfWhisperEncoder.bin} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e15bf25a17c138e7344b2b21d54e980ab398cb1edabba2842d75ef0bac155eff
3
- size 93904432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7619b8b8d188f1a2f9f92edff8416ecff6eebfe37dbce8ab6b278b5072be32d4
3
+ size 63795200
Whisper-Base-En_WhisperEncoderInf.dlc → precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_HfWhisperEncoder.onnx.zip RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9517e974c58d34d3d37cca6e21a1b53486a3048c99055944da66d53978bcf480
3
- size 47857903
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf8ca6fdc4050505ab8ead6ea33397211b150c5ac9990602a1a2e38f7e4e268
3
+ size 47065603
precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_WhisperDecoderInf.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf3e35f47fcd7c8d2a6271259b46e4a4732a8b747ba1c58a234df0707b69291f
3
- size 152267392
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_WhisperDecoderInf.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbdc902fcadf9c24319aa0a1f7e300f3e926a79f18d8830ec1b46498738b49e3
3
- size 137760824
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/Whisper-Base-En_WhisperEncoderInf.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:02a0a9459561ef91af9c18a177aeb843c45caa4b54f8ef64d4605dd3c54d68b7
3
- size 55305196
 
 
 
 
precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml CHANGED
@@ -1,5 +1,5 @@
1
  sdk_versions:
2
  qnn_context_binary:
3
- qairt: 2.34.2.250528164111_119506
4
  precompiled_qnn_onnx:
5
  qairt: 2.33.2.250410134701_117956
 
1
  sdk_versions:
2
  qnn_context_binary:
3
+ qairt: 2.37.0.250724175447_124859
4
  precompiled_qnn_onnx:
5
  qairt: 2.33.2.250410134701_117956
sdk_versions.yml ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ sdk_versions:
2
+ tflite:
3
+ tflite: 2.17.0
4
+ qnn_dlc:
5
+ qairt: 2.37.0.250724175447_124859