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
d98cc85
·
verified ·
1 Parent(s): 50557a4

v0.61.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (3) hide show
  1. LICENSE +1 -0
  2. README.md +117 -0
  3. release_assets.json +28 -0
LICENSE ADDED
@@ -0,0 +1 @@
 
 
1
+ The license of the original trained model can be found at https://github.com/modelscope/FunASR?tab=MIT-1-ov-file.
README.md ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: pytorch
3
+ license: mit
4
+ tags:
5
+ - real_time
6
+ - android
7
+ pipeline_tag: automatic-speech-recognition
8
+
9
+ ---
10
+
11
+ ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/web-assets/model_demo.png)
12
+
13
+ # FunASR-Conformer-EN: Optimized for Qualcomm Devices
14
+
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/v0.61.0/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
+
22
+ ## Getting Started
23
+ There are two ways to deploy this model on your device:
24
+
25
+ ### Option 1: Download Pre-Exported Models
26
+
27
+ Below are pre-exported model assets ready for deployment.
28
+
29
+ | Runtime | Precision | Chipset | SDK Versions | Download |
30
+ |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.61.0/funasr_conformer_en-onnx-float.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.61.0/funasr_conformer_en-qnn_dlc-float.zip)
33
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.61.0/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/v0.61.0/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/v0.61.0/src/qai_hub_models/models/funasr_conformer_en) for usage instructions.
48
+
49
+ ## Model Details
50
+
51
+ **Model Type:** Model_use_case.speech_recognition
52
+
53
+ **Model Stats:**
54
+ - Input resolution: 1x160000 (10s at 16kHz)
55
+ - Model checkpoint: funasr/conformer-en
56
+ - Model size (float): ~840 MB
57
+ - Number of parameters: 220M
58
+
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® X2 Elite | 24.852 ms | 9 - 9 MB | NPU
63
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® X Elite | 50.732 ms | 326 - 326 MB | NPU
64
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 33.644 ms | 7 - 1060 MB | NPU
65
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 69.257 ms | 6 - 1029 MB | NPU
66
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 54.153 ms | 6 - 9 MB | NPU
67
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 47.515 ms | 0 - 387 MB | NPU
68
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® QCS8450 | 69.257 ms | 6 - 1029 MB | NPU
69
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 54.526 ms | 6 - 9 MB | NPU
70
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 50.732 ms | 326 - 326 MB | NPU
71
+ | FunASR-Conformer-EN | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 24.062 ms | 7 - 722 MB | NPU
72
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Elite Mobile | 24.062 ms | 7 - 722 MB | NPU
73
+ | FunASR-Conformer-EN | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 19.34 ms | 6 - 704 MB | NPU
74
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® X2 Elite | 23.738 ms | 0 - 0 MB | NPU
75
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® X Elite | 47.954 ms | 0 - 0 MB | NPU
76
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 31.812 ms | 0 - 953 MB | NPU
77
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 65.029 ms | 1 - 922 MB | NPU
78
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 112.899 ms | 1 - 654 MB | NPU
79
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 44.742 ms | 1 - 756 MB | NPU
80
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8775P | 51.223 ms | 1 - 653 MB | NPU
81
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8650P | 51.223 ms | 1 - 653 MB | NPU
82
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8255P | 51.223 ms | 1 - 653 MB | NPU
83
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® QCS8450 | 65.029 ms | 1 - 922 MB | NPU
84
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 67.266 ms | 2 - 7 MB | NPU
85
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 47.954 ms | 0 - 0 MB | NPU
86
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 23.406 ms | 0 - 652 MB | NPU
87
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA7255P | 112.899 ms | 1 - 654 MB | NPU
88
+ | FunASR-Conformer-EN | QNN_DLC | float | Qualcomm® SA8295P | 55.177 ms | 1 - 660 MB | NPU
89
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 23.406 ms | 0 - 652 MB | NPU
90
+ | FunASR-Conformer-EN | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.134 ms | 0 - 609 MB | NPU
91
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.051 ms | 3 - 1029 MB | NPU
92
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 65.923 ms | 4 - 984 MB | NPU
93
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 51.053 ms | 3 - 335 MB | NPU
94
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 112.966 ms | 3 - 683 MB | NPU
95
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 44.304 ms | 3 - 7 MB | NPU
96
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8775P | 51.703 ms | 3 - 684 MB | NPU
97
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8650P | 51.703 ms | 3 - 684 MB | NPU
98
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8255P | 51.703 ms | 3 - 684 MB | NPU
99
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® QCS8450 | 65.923 ms | 4 - 984 MB | NPU
100
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 52.859 ms | 3 - 335 MB | NPU
101
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 23.368 ms | 3 - 690 MB | NPU
102
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA7255P | 112.966 ms | 3 - 683 MB | NPU
103
+ | FunASR-Conformer-EN | TFLITE | float | Qualcomm® SA8295P | 55.196 ms | 3 - 689 MB | NPU
104
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Elite Mobile | 23.368 ms | 3 - 690 MB | NPU
105
+ | FunASR-Conformer-EN | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.073 ms | 3 - 644 MB | NPU
106
+
107
+ ## License
108
+ * The license for the original implementation of FunASR-Conformer-EN can be found
109
+ [here](https://github.com/modelscope/FunASR?tab=MIT-1-ov-file).
110
+
111
+ ## References
112
+ * [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
113
+ * [Source Model Implementation](https://huggingface.co/funasr/conformer-en)
114
+
115
+ ## Community
116
+ * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
117
+ * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
release_assets.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.61.0",
3
+ "precisions": {
4
+ "float": {
5
+ "universal_assets": {
6
+ "onnx": {
7
+ "tool_versions": {
8
+ "qairt": "2.45.0.260326154327",
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/v0.61.0/funasr_conformer_en-onnx-float.zip"
12
+ },
13
+ "qnn_dlc": {
14
+ "tool_versions": {
15
+ "qairt": "2.45.0.260326154327"
16
+ },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.61.0/funasr_conformer_en-qnn_dlc-float.zip"
18
+ },
19
+ "tflite": {
20
+ "tool_versions": {
21
+ "qairt": "2.45.0.260326154327"
22
+ },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/funasr_conformer_en/releases/v0.61.0/funasr_conformer_en-tflite-float.zip"
24
+ }
25
+ }
26
+ }
27
+ }
28
+ }