Hugging Face's logo

qualcomm
/
FunASR-Conformer-EN

Automatic Speech Recognition
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
32798bc
·
verified ·
1 Parent(s): 2aad44c

v0.64.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.64.0 for changelog.

Files changed (2) hide show
  1. README.md +48 -45
  2. release_assets.json +5 -5
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: automatic-speech-recognition
15
  FunASR Conformer-EN is a large-scale English ASR model from Alibaba DAMO Academy, trained on ~50,000 hours of English speech. It uses a 32-block Conformer encoder(512 hidden dim, 16 attention heads) with a CTC head for decoding. The model accepts raw 16kHz audio and outputs transcribed text via CTC greedy decoding.
16
 
17
  This is based on the implementation of FunASR-Conformer-EN found [here](https://huggingface.co/funasr/conformer-en).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/funasr_conformer_en) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
@@ -28,23 +28,23 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.63.0/funasr_conformer_en-onnx-float.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.63.0/funasr_conformer_en-qnn_dlc-float.zip)
33
- | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.63.0/funasr_conformer_en-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[FunASR-Conformer-EN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/funasr_conformer_en)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/funasr_conformer_en) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
- See our repository for [FunASR-Conformer-EN on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/funasr_conformer_en) for usage instructions.
48
 
49
  ## Model Details
50
 
@@ -59,45 +59,48 @@ See our repository for [FunASR-Conformer-EN on GitHub](https://github.com/qualco
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
- | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 17.576 ms | 6 - 659 MB | NPU
63
- | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 22.504 ms | 6 - 637 MB | NPU
64
- | FunASR-Conformer-EN | ONNX | float | Snapdragon® X2 Elite | 23.161 ms | 9 - 9 MB | NPU
65
- | FunASR-Conformer-EN | ONNX | float | Snapdragon® X Elite | 44.434 ms | 325 - 325 MB | NPU
66
- | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 30.544 ms | 8 - 980 MB | NPU
67
- | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 55.817 ms | 6 - 990 MB | NPU
68
- | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 48.118 ms | 5 - 10 MB | NPU
69
- | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 40.864 ms | 0 - 387 MB | NPU
70
- | FunASR-Conformer-EN | ONNX | float | Qualcomm® QCS8450 | 55.817 ms | 6 - 990 MB | NPU
71
- | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 49.29 ms | 6 - 10 MB | NPU
72
- | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.434 ms | 325 - 325 MB | NPU
73
- | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 22.504 ms | 6 - 637 MB | NPU
74
- | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 18.035 ms | 0 - 596 MB | NPU
75
- | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 22.912 ms | 0 - 592 MB | NPU
76
- | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® X2 Elite | 23.844 ms | 0 - 0 MB | NPU
77
- | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® X Elite | 44.805 ms | 0 - 0 MB | NPU
78
- | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 30.33 ms | 1 - 896 MB | NPU
79
- | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 57.557 ms | 0 - 905 MB | NPU
80
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 48.282 ms | 0 - 7 MB | NPU
81
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 40.752 ms | 1 - 3 MB | NPU
82
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® QCS8450 | 57.557 ms | 0 - 905 MB | NPU
83
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 49.067 ms | 2 - 8 MB | NPU
84
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.805 ms | 0 - 0 MB | NPU
85
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 22.912 ms | 0 - 592 MB | NPU
86
- | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8295P | 54.397 ms | 1 - 595 MB | NPU
87
- | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 18.027 ms | 3 - 626 MB | NPU
88
- | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 22.862 ms | 3 - 622 MB | NPU
89
- | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 30.43 ms | 3 - 963 MB | NPU
90
- | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 56.922 ms | 3 - 959 MB | NPU
91
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 48.473 ms | 3 - 335 MB | NPU
92
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.152 ms | 0 - 4 MB | NPU
93
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8775P | 48.186 ms | 3 - 621 MB | NPU
94
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8650P | 48.186 ms | 3 - 621 MB | NPU
95
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8255P | 48.186 ms | 3 - 621 MB | NPU
96
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® QCS8450 | 56.922 ms | 3 - 959 MB | NPU
97
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 48.86 ms | 3 - 335 MB | NPU
98
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 22.862 ms | 3 - 622 MB | NPU
99
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA7255P | 106.305 ms | 3 - 622 MB | NPU
100
- | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8295P | 54.877 ms | 3 - 615 MB | NPU
 
 
 
101
 
102
  ## License
103
  * The license for the original implementation of FunASR-Conformer-EN can be found
 
15
  FunASR Conformer-EN is a large-scale English ASR model from Alibaba DAMO Academy, trained on ~50,000 hours of English speech. It uses a 32-block Conformer encoder(512 hidden dim, 16 attention heads) with a CTC head for decoding. The model accepts raw 16kHz audio and outputs transcribed text via CTC greedy decoding.
16
 
17
  This is based on the implementation of FunASR-Conformer-EN found [here](https://huggingface.co/funasr/conformer-en).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/funasr_conformer_en) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.64.0/funasr_conformer_en-onnx-float.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.64.0/funasr_conformer_en-qnn_dlc-float.zip)
33
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.64.0/funasr_conformer_en-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[FunASR-Conformer-EN on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/funasr_conformer_en)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/funasr_conformer_en) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
+ See our repository for [FunASR-Conformer-EN on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.64.0/src/qai_hub_models/models/funasr_conformer_en) for usage instructions.
48
 
49
  ## Model Details
50
 
 
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 17.511 ms | 7 - 665 MB | NPU
63
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 22.422 ms | 7 - 640 MB | NPU
64
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® X2 Elite | 23.178 ms | 9 - 9 MB | NPU
65
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® X Elite | 44.406 ms | 325 - 325 MB | NPU
66
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 30.573 ms | 3 - 978 MB | NPU
67
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 57.25 ms | 6 - 996 MB | NPU
68
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 48.247 ms | 5 - 10 MB | NPU
69
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 40.58 ms | 0 - 387 MB | NPU
70
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® QCS8450 | 57.25 ms | 6 - 996 MB | NPU
71
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 49.793 ms | 7 - 11 MB | NPU
72
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.406 ms | 325 - 325 MB | NPU
73
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 22.422 ms | 7 - 640 MB | NPU
74
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 18.032 ms | 0 - 595 MB | NPU
75
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 22.902 ms | 0 - 591 MB | NPU
76
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® X2 Elite | 24.057 ms | 0 - 0 MB | NPU
77
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® X Elite | 44.866 ms | 0 - 0 MB | NPU
78
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 30.241 ms | 0 - 891 MB | NPU
79
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 57.241 ms | 0 - 904 MB | NPU
80
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 48.488 ms | 0 - 6 MB | NPU
81
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.729 ms | 1 - 7 MB | NPU
82
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8775P | 47.827 ms | 1 - 593 MB | NPU
83
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8650P | 47.827 ms | 1 - 593 MB | NPU
84
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8255P | 47.827 ms | 1 - 593 MB | NPU
85
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® QCS8450 | 57.241 ms | 0 - 904 MB | NPU
86
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 49.666 ms | 0 - 6 MB | NPU
87
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.866 ms | 0 - 0 MB | NPU
88
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 22.902 ms | 0 - 591 MB | NPU
89
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8295P | 54.375 ms | 1 - 595 MB | NPU
90
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 18.067 ms | 3 - 624 MB | NPU
91
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 22.874 ms | 3 - 619 MB | NPU
92
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 30.221 ms | 0 - 955 MB | NPU
93
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 57.359 ms | 3 - 961 MB | NPU
94
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 48.261 ms | 3 - 335 MB | NPU
95
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.431 ms | 3 - 8 MB | NPU
96
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8775P | 48.047 ms | 3 - 621 MB | NPU
97
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8650P | 48.047 ms | 3 - 621 MB | NPU
98
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8255P | 48.047 ms | 3 - 621 MB | NPU
99
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® QCS8450 | 57.359 ms | 3 - 961 MB | NPU
100
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 48.876 ms | 3 - 335 MB | NPU
101
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 22.874 ms | 3 - 619 MB | NPU
102
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA7255P | 106.572 ms | 3 - 621 MB | NPU
103
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8295P | 54.635 ms | 3 - 614 MB | NPU
104
 
105
  ## License
106
  * The license for the original implementation of FunASR-Conformer-EN can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
  "qairt": "2.50.0.260828221209",
9
- "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.63.0/funasr_conformer_en-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.50.0.260828221209"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.63.0/funasr_conformer_en-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.50.0.260828221209"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.63.0/funasr_conformer_en-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.64.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
  "qairt": "2.50.0.260828221209",
9
+ "onnx_runtime": "1.30.0"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.64.0/funasr_conformer_en-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.64.0/funasr_conformer_en-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.64.0/funasr_conformer_en-tflite-float.zip"
24
  }
25
  }
26
  }