v0.66.0
Browse filesSee https://github.com/qualcomm/ai-hub-models/releases/v0.66.0 for changelog.
- README.md +42 -42
- release_assets.json +40 -40
README.md
CHANGED
|
@@ -15,7 +15,7 @@ pipeline_tag: automatic-speech-recognition
|
|
| 15 |
Zipformer streaming ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text streamingly. This model is based on the transformer architecture and has been optimized for edge inference by replacing 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 audios. Time to the first token is the encoder's latency, while time to each additional token is joiner's latency, where we assume a max decoded length specified below.
|
| 16 |
|
| 17 |
This is based on the implementation of Zipformer found [here](https://github.com/k2-fsa/icefall).
|
| 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.
|
| 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 |
|
|
@@ -28,59 +28,59 @@ Below are pre-exported model assets ready for deployment.
|
|
| 28 |
|
| 29 |
| Runtime | Precision | Chipset | SDK Versions | Download |
|
| 30 |
|---|---|---|---|---|
|
| 31 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 32 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 33 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 34 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 35 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 36 |
-
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 37 |
-
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 38 |
-
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 39 |
-
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 40 |
-
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 41 |
-
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 42 |
-
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 43 |
-
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 44 |
-
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 45 |
-
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 46 |
-
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 47 |
-
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 48 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 49 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 50 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 51 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 52 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 53 |
-
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 54 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 55 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 56 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 57 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 58 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 59 |
-
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 60 |
-
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 61 |
-
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 62 |
-
| QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 63 |
-
| QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 64 |
-
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 65 |
-
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 66 |
-
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 67 |
-
| QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 68 |
-
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 69 |
-
| QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 70 |
|
| 71 |
For more device-specific assets and performance metrics, visit **[Zipformer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/zipformer)**.
|
| 72 |
|
| 73 |
|
| 74 |
### Option 2: Export with Custom Configurations
|
| 75 |
|
| 76 |
-
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 77 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 78 |
- Custom input shapes
|
| 79 |
- Target device and runtime configurations
|
| 80 |
|
| 81 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 82 |
|
| 83 |
-
See our repository for [Zipformer on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.
|
| 84 |
|
| 85 |
## Model Details
|
| 86 |
|
|
|
|
| 15 |
Zipformer streaming ASR (Automatic Speech Recognition) model is a state-of-the-art system designed for transcribing spoken language into written text streamingly. This model is based on the transformer architecture and has been optimized for edge inference by replacing 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 audios. Time to the first token is the encoder's latency, while time to each additional token is joiner's latency, where we assume a max decoded length specified below.
|
| 16 |
|
| 17 |
This is based on the implementation of Zipformer found [here](https://github.com/k2-fsa/icefall).
|
| 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/v0.66.0/src/qai_hub_models/models/zipformer) 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 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
|
| 32 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 33 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
|
| 34 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
|
| 35 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
|
| 36 |
+
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
|
| 37 |
+
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip)
|
| 38 |
+
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
|
| 39 |
+
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
|
| 40 |
+
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
|
| 41 |
+
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 42 |
+
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X2 Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_x2_elite.zip)
|
| 43 |
+
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® X Elite | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_x_elite.zip)
|
| 44 |
+
| PRECOMPILED_QNN_ONNX | mixed | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_8gen3.zip)
|
| 45 |
+
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_qcs8275.zip)
|
| 46 |
+
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_qcs8550_proxy.zip)
|
| 47 |
+
| PRECOMPILED_QNN_ONNX | mixed | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50, ONNX Runtime 1.30.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_qcs9075.zip)
|
| 48 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
|
| 49 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 50 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
|
| 51 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
|
| 52 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
|
| 53 |
+
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
|
| 54 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_qcs8275.zip)
|
| 55 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
|
| 56 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_sa8775p.zip)
|
| 57 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_qcs9075.zip)
|
| 58 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_sa7255p.zip)
|
| 59 |
+
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_sa8295p.zip)
|
| 60 |
+
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
|
| 61 |
+
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_8_elite_for_galaxy.zip)
|
| 62 |
+
| QNN_CONTEXT_BINARY | mixed | Snapdragon® X2 Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_x2_elite.zip)
|
| 63 |
+
| QNN_CONTEXT_BINARY | mixed | Snapdragon® X Elite | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_x_elite.zip)
|
| 64 |
+
| QNN_CONTEXT_BINARY | mixed | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_8gen3.zip)
|
| 65 |
+
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_qcs8275.zip)
|
| 66 |
+
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_qcs8550_proxy.zip)
|
| 67 |
+
| QNN_CONTEXT_BINARY | mixed | Qualcomm® SA8775P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_sa8775p.zip)
|
| 68 |
+
| QNN_CONTEXT_BINARY | mixed | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_qcs9075.zip)
|
| 69 |
+
| QNN_CONTEXT_BINARY | mixed | Qualcomm® SA7255P | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_sa7255p.zip)
|
| 70 |
|
| 71 |
For more device-specific assets and performance metrics, visit **[Zipformer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/zipformer)**.
|
| 72 |
|
| 73 |
|
| 74 |
### Option 2: Export with Custom Configurations
|
| 75 |
|
| 76 |
+
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.66.0/src/qai_hub_models/models/zipformer) Python library to compile and export the model with your own:
|
| 77 |
- Custom weights (e.g., fine-tuned checkpoints)
|
| 78 |
- Custom input shapes
|
| 79 |
- Target device and runtime configurations
|
| 80 |
|
| 81 |
This option is ideal if you need to customize the model beyond the default configuration provided here.
|
| 82 |
|
| 83 |
+
See our repository for [Zipformer on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.66.0/src/qai_hub_models/models/zipformer) for usage instructions.
|
| 84 |
|
| 85 |
## Model Details
|
| 86 |
|
release_assets.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"version": "0.
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"chipset_assets": {
|
|
@@ -9,13 +9,13 @@
|
|
| 9 |
"qairt": "2.50.0.260828221209",
|
| 10 |
"onnx_runtime": "1.30.0"
|
| 11 |
},
|
| 12 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 13 |
},
|
| 14 |
"qnn_context_binary": {
|
| 15 |
"tool_versions": {
|
| 16 |
"qairt": "2.50.0.260828221209"
|
| 17 |
},
|
| 18 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 19 |
}
|
| 20 |
},
|
| 21 |
"qualcomm-qcs8550-proxy": {
|
|
@@ -24,13 +24,13 @@
|
|
| 24 |
"qairt": "2.50.0.260828221209",
|
| 25 |
"onnx_runtime": "1.30.0"
|
| 26 |
},
|
| 27 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 28 |
},
|
| 29 |
"qnn_context_binary": {
|
| 30 |
"tool_versions": {
|
| 31 |
"qairt": "2.50.0.260828221209"
|
| 32 |
},
|
| 33 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"qualcomm-qcs9075": {
|
|
@@ -39,13 +39,13 @@
|
|
| 39 |
"qairt": "2.50.0.260828221209",
|
| 40 |
"onnx_runtime": "1.30.0"
|
| 41 |
},
|
| 42 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 43 |
},
|
| 44 |
"qnn_context_binary": {
|
| 45 |
"tool_versions": {
|
| 46 |
"qairt": "2.50.0.260828221209"
|
| 47 |
},
|
| 48 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 49 |
}
|
| 50 |
},
|
| 51 |
"qualcomm-sa7255p": {
|
|
@@ -53,7 +53,7 @@
|
|
| 53 |
"tool_versions": {
|
| 54 |
"qairt": "2.50.0.260828221209"
|
| 55 |
},
|
| 56 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 57 |
}
|
| 58 |
},
|
| 59 |
"qualcomm-sa8295p": {
|
|
@@ -61,7 +61,7 @@
|
|
| 61 |
"tool_versions": {
|
| 62 |
"qairt": "2.50.0.260828221209"
|
| 63 |
},
|
| 64 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 65 |
}
|
| 66 |
},
|
| 67 |
"qualcomm-sa8775p": {
|
|
@@ -69,7 +69,7 @@
|
|
| 69 |
"tool_versions": {
|
| 70 |
"qairt": "2.50.0.260828221209"
|
| 71 |
},
|
| 72 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 73 |
}
|
| 74 |
},
|
| 75 |
"qualcomm-snapdragon-8-elite-for-galaxy": {
|
|
@@ -78,13 +78,13 @@
|
|
| 78 |
"qairt": "2.50.0.260828221209",
|
| 79 |
"onnx_runtime": "1.30.0"
|
| 80 |
},
|
| 81 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 82 |
},
|
| 83 |
"qnn_context_binary": {
|
| 84 |
"tool_versions": {
|
| 85 |
"qairt": "2.50.0.260828221209"
|
| 86 |
},
|
| 87 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 88 |
}
|
| 89 |
},
|
| 90 |
"qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
|
|
@@ -93,13 +93,13 @@
|
|
| 93 |
"qairt": "2.50.0.260828221209",
|
| 94 |
"onnx_runtime": "1.30.0"
|
| 95 |
},
|
| 96 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 97 |
},
|
| 98 |
"qnn_context_binary": {
|
| 99 |
"tool_versions": {
|
| 100 |
"qairt": "2.50.0.260828221209"
|
| 101 |
},
|
| 102 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 103 |
}
|
| 104 |
},
|
| 105 |
"qualcomm-snapdragon-8gen1": {
|
|
@@ -108,13 +108,13 @@
|
|
| 108 |
"qairt": "2.50.0.260828221209",
|
| 109 |
"onnx_runtime": "1.30.0"
|
| 110 |
},
|
| 111 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 112 |
},
|
| 113 |
"qnn_context_binary": {
|
| 114 |
"tool_versions": {
|
| 115 |
"qairt": "2.50.0.260828221209"
|
| 116 |
},
|
| 117 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 118 |
}
|
| 119 |
},
|
| 120 |
"qualcomm-snapdragon-8gen3": {
|
|
@@ -123,13 +123,13 @@
|
|
| 123 |
"qairt": "2.50.0.260828221209",
|
| 124 |
"onnx_runtime": "1.30.0"
|
| 125 |
},
|
| 126 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 127 |
},
|
| 128 |
"qnn_context_binary": {
|
| 129 |
"tool_versions": {
|
| 130 |
"qairt": "2.50.0.260828221209"
|
| 131 |
},
|
| 132 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 133 |
}
|
| 134 |
},
|
| 135 |
"qualcomm-snapdragon-x-elite": {
|
|
@@ -138,13 +138,13 @@
|
|
| 138 |
"qairt": "2.50.0.260828221209",
|
| 139 |
"onnx_runtime": "1.30.0"
|
| 140 |
},
|
| 141 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 142 |
},
|
| 143 |
"qnn_context_binary": {
|
| 144 |
"tool_versions": {
|
| 145 |
"qairt": "2.50.0.260828221209"
|
| 146 |
},
|
| 147 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 148 |
}
|
| 149 |
},
|
| 150 |
"qualcomm-snapdragon-x2-elite": {
|
|
@@ -153,13 +153,13 @@
|
|
| 153 |
"qairt": "2.50.0.260828221209",
|
| 154 |
"onnx_runtime": "1.30.0"
|
| 155 |
},
|
| 156 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 157 |
},
|
| 158 |
"qnn_context_binary": {
|
| 159 |
"tool_versions": {
|
| 160 |
"qairt": "2.50.0.260828221209"
|
| 161 |
},
|
| 162 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 163 |
}
|
| 164 |
}
|
| 165 |
}
|
|
@@ -172,13 +172,13 @@
|
|
| 172 |
"qairt": "2.50.0.260828221209",
|
| 173 |
"onnx_runtime": "1.30.0"
|
| 174 |
},
|
| 175 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 176 |
},
|
| 177 |
"qnn_context_binary": {
|
| 178 |
"tool_versions": {
|
| 179 |
"qairt": "2.50.0.260828221209"
|
| 180 |
},
|
| 181 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 182 |
}
|
| 183 |
},
|
| 184 |
"qualcomm-qcs8550-proxy": {
|
|
@@ -187,13 +187,13 @@
|
|
| 187 |
"qairt": "2.50.0.260828221209",
|
| 188 |
"onnx_runtime": "1.30.0"
|
| 189 |
},
|
| 190 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 191 |
},
|
| 192 |
"qnn_context_binary": {
|
| 193 |
"tool_versions": {
|
| 194 |
"qairt": "2.50.0.260828221209"
|
| 195 |
},
|
| 196 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 197 |
}
|
| 198 |
},
|
| 199 |
"qualcomm-qcs9075": {
|
|
@@ -202,13 +202,13 @@
|
|
| 202 |
"qairt": "2.50.0.260828221209",
|
| 203 |
"onnx_runtime": "1.30.0"
|
| 204 |
},
|
| 205 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 206 |
},
|
| 207 |
"qnn_context_binary": {
|
| 208 |
"tool_versions": {
|
| 209 |
"qairt": "2.50.0.260828221209"
|
| 210 |
},
|
| 211 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 212 |
}
|
| 213 |
},
|
| 214 |
"qualcomm-sa7255p": {
|
|
@@ -216,7 +216,7 @@
|
|
| 216 |
"tool_versions": {
|
| 217 |
"qairt": "2.50.0.260828221209"
|
| 218 |
},
|
| 219 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 220 |
}
|
| 221 |
},
|
| 222 |
"qualcomm-sa8775p": {
|
|
@@ -224,7 +224,7 @@
|
|
| 224 |
"tool_versions": {
|
| 225 |
"qairt": "2.50.0.260828221209"
|
| 226 |
},
|
| 227 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 228 |
}
|
| 229 |
},
|
| 230 |
"qualcomm-snapdragon-8-elite-for-galaxy": {
|
|
@@ -233,13 +233,13 @@
|
|
| 233 |
"qairt": "2.50.0.260828221209",
|
| 234 |
"onnx_runtime": "1.30.0"
|
| 235 |
},
|
| 236 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 237 |
},
|
| 238 |
"qnn_context_binary": {
|
| 239 |
"tool_versions": {
|
| 240 |
"qairt": "2.50.0.260828221209"
|
| 241 |
},
|
| 242 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 243 |
}
|
| 244 |
},
|
| 245 |
"qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
|
|
@@ -248,13 +248,13 @@
|
|
| 248 |
"qairt": "2.50.0.260828221209",
|
| 249 |
"onnx_runtime": "1.30.0"
|
| 250 |
},
|
| 251 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 252 |
},
|
| 253 |
"qnn_context_binary": {
|
| 254 |
"tool_versions": {
|
| 255 |
"qairt": "2.50.0.260828221209"
|
| 256 |
},
|
| 257 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 258 |
}
|
| 259 |
},
|
| 260 |
"qualcomm-snapdragon-8gen3": {
|
|
@@ -263,13 +263,13 @@
|
|
| 263 |
"qairt": "2.50.0.260828221209",
|
| 264 |
"onnx_runtime": "1.30.0"
|
| 265 |
},
|
| 266 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 267 |
},
|
| 268 |
"qnn_context_binary": {
|
| 269 |
"tool_versions": {
|
| 270 |
"qairt": "2.50.0.260828221209"
|
| 271 |
},
|
| 272 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 273 |
}
|
| 274 |
},
|
| 275 |
"qualcomm-snapdragon-x-elite": {
|
|
@@ -278,13 +278,13 @@
|
|
| 278 |
"qairt": "2.50.0.260828221209",
|
| 279 |
"onnx_runtime": "1.30.0"
|
| 280 |
},
|
| 281 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 282 |
},
|
| 283 |
"qnn_context_binary": {
|
| 284 |
"tool_versions": {
|
| 285 |
"qairt": "2.50.0.260828221209"
|
| 286 |
},
|
| 287 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 288 |
}
|
| 289 |
},
|
| 290 |
"qualcomm-snapdragon-x2-elite": {
|
|
@@ -293,13 +293,13 @@
|
|
| 293 |
"qairt": "2.50.0.260828221209",
|
| 294 |
"onnx_runtime": "1.30.0"
|
| 295 |
},
|
| 296 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 297 |
},
|
| 298 |
"qnn_context_binary": {
|
| 299 |
"tool_versions": {
|
| 300 |
"qairt": "2.50.0.260828221209"
|
| 301 |
},
|
| 302 |
-
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.
|
| 303 |
}
|
| 304 |
}
|
| 305 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"version": "0.66.0",
|
| 3 |
"precisions": {
|
| 4 |
"float": {
|
| 5 |
"chipset_assets": {
|
|
|
|
| 9 |
"qairt": "2.50.0.260828221209",
|
| 10 |
"onnx_runtime": "1.30.0"
|
| 11 |
},
|
| 12 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip"
|
| 13 |
},
|
| 14 |
"qnn_context_binary": {
|
| 15 |
"tool_versions": {
|
| 16 |
"qairt": "2.50.0.260828221209"
|
| 17 |
},
|
| 18 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_qcs8275.zip"
|
| 19 |
}
|
| 20 |
},
|
| 21 |
"qualcomm-qcs8550-proxy": {
|
|
|
|
| 24 |
"qairt": "2.50.0.260828221209",
|
| 25 |
"onnx_runtime": "1.30.0"
|
| 26 |
},
|
| 27 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip"
|
| 28 |
},
|
| 29 |
"qnn_context_binary": {
|
| 30 |
"tool_versions": {
|
| 31 |
"qairt": "2.50.0.260828221209"
|
| 32 |
},
|
| 33 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip"
|
| 34 |
}
|
| 35 |
},
|
| 36 |
"qualcomm-qcs9075": {
|
|
|
|
| 39 |
"qairt": "2.50.0.260828221209",
|
| 40 |
"onnx_runtime": "1.30.0"
|
| 41 |
},
|
| 42 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip"
|
| 43 |
},
|
| 44 |
"qnn_context_binary": {
|
| 45 |
"tool_versions": {
|
| 46 |
"qairt": "2.50.0.260828221209"
|
| 47 |
},
|
| 48 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_qcs9075.zip"
|
| 49 |
}
|
| 50 |
},
|
| 51 |
"qualcomm-sa7255p": {
|
|
|
|
| 53 |
"tool_versions": {
|
| 54 |
"qairt": "2.50.0.260828221209"
|
| 55 |
},
|
| 56 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_sa7255p.zip"
|
| 57 |
}
|
| 58 |
},
|
| 59 |
"qualcomm-sa8295p": {
|
|
|
|
| 61 |
"tool_versions": {
|
| 62 |
"qairt": "2.50.0.260828221209"
|
| 63 |
},
|
| 64 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_sa8295p.zip"
|
| 65 |
}
|
| 66 |
},
|
| 67 |
"qualcomm-sa8775p": {
|
|
|
|
| 69 |
"tool_versions": {
|
| 70 |
"qairt": "2.50.0.260828221209"
|
| 71 |
},
|
| 72 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_sa8775p.zip"
|
| 73 |
}
|
| 74 |
},
|
| 75 |
"qualcomm-snapdragon-8-elite-for-galaxy": {
|
|
|
|
| 78 |
"qairt": "2.50.0.260828221209",
|
| 79 |
"onnx_runtime": "1.30.0"
|
| 80 |
},
|
| 81 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
|
| 82 |
},
|
| 83 |
"qnn_context_binary": {
|
| 84 |
"tool_versions": {
|
| 85 |
"qairt": "2.50.0.260828221209"
|
| 86 |
},
|
| 87 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
|
| 88 |
}
|
| 89 |
},
|
| 90 |
"qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
|
|
|
|
| 93 |
"qairt": "2.50.0.260828221209",
|
| 94 |
"onnx_runtime": "1.30.0"
|
| 95 |
},
|
| 96 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
|
| 97 |
},
|
| 98 |
"qnn_context_binary": {
|
| 99 |
"tool_versions": {
|
| 100 |
"qairt": "2.50.0.260828221209"
|
| 101 |
},
|
| 102 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
|
| 103 |
}
|
| 104 |
},
|
| 105 |
"qualcomm-snapdragon-8gen1": {
|
|
|
|
| 108 |
"qairt": "2.50.0.260828221209",
|
| 109 |
"onnx_runtime": "1.30.0"
|
| 110 |
},
|
| 111 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip"
|
| 112 |
},
|
| 113 |
"qnn_context_binary": {
|
| 114 |
"tool_versions": {
|
| 115 |
"qairt": "2.50.0.260828221209"
|
| 116 |
},
|
| 117 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip"
|
| 118 |
}
|
| 119 |
},
|
| 120 |
"qualcomm-snapdragon-8gen3": {
|
|
|
|
| 123 |
"qairt": "2.50.0.260828221209",
|
| 124 |
"onnx_runtime": "1.30.0"
|
| 125 |
},
|
| 126 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip"
|
| 127 |
},
|
| 128 |
"qnn_context_binary": {
|
| 129 |
"tool_versions": {
|
| 130 |
"qairt": "2.50.0.260828221209"
|
| 131 |
},
|
| 132 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip"
|
| 133 |
}
|
| 134 |
},
|
| 135 |
"qualcomm-snapdragon-x-elite": {
|
|
|
|
| 138 |
"qairt": "2.50.0.260828221209",
|
| 139 |
"onnx_runtime": "1.30.0"
|
| 140 |
},
|
| 141 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip"
|
| 142 |
},
|
| 143 |
"qnn_context_binary": {
|
| 144 |
"tool_versions": {
|
| 145 |
"qairt": "2.50.0.260828221209"
|
| 146 |
},
|
| 147 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip"
|
| 148 |
}
|
| 149 |
},
|
| 150 |
"qualcomm-snapdragon-x2-elite": {
|
|
|
|
| 153 |
"qairt": "2.50.0.260828221209",
|
| 154 |
"onnx_runtime": "1.30.0"
|
| 155 |
},
|
| 156 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip"
|
| 157 |
},
|
| 158 |
"qnn_context_binary": {
|
| 159 |
"tool_versions": {
|
| 160 |
"qairt": "2.50.0.260828221209"
|
| 161 |
},
|
| 162 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip"
|
| 163 |
}
|
| 164 |
}
|
| 165 |
}
|
|
|
|
| 172 |
"qairt": "2.50.0.260828221209",
|
| 173 |
"onnx_runtime": "1.30.0"
|
| 174 |
},
|
| 175 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_qcs8275.zip"
|
| 176 |
},
|
| 177 |
"qnn_context_binary": {
|
| 178 |
"tool_versions": {
|
| 179 |
"qairt": "2.50.0.260828221209"
|
| 180 |
},
|
| 181 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_qcs8275.zip"
|
| 182 |
}
|
| 183 |
},
|
| 184 |
"qualcomm-qcs8550-proxy": {
|
|
|
|
| 187 |
"qairt": "2.50.0.260828221209",
|
| 188 |
"onnx_runtime": "1.30.0"
|
| 189 |
},
|
| 190 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_qcs8550_proxy.zip"
|
| 191 |
},
|
| 192 |
"qnn_context_binary": {
|
| 193 |
"tool_versions": {
|
| 194 |
"qairt": "2.50.0.260828221209"
|
| 195 |
},
|
| 196 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_qcs8550_proxy.zip"
|
| 197 |
}
|
| 198 |
},
|
| 199 |
"qualcomm-qcs9075": {
|
|
|
|
| 202 |
"qairt": "2.50.0.260828221209",
|
| 203 |
"onnx_runtime": "1.30.0"
|
| 204 |
},
|
| 205 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_qcs9075.zip"
|
| 206 |
},
|
| 207 |
"qnn_context_binary": {
|
| 208 |
"tool_versions": {
|
| 209 |
"qairt": "2.50.0.260828221209"
|
| 210 |
},
|
| 211 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_qcs9075.zip"
|
| 212 |
}
|
| 213 |
},
|
| 214 |
"qualcomm-sa7255p": {
|
|
|
|
| 216 |
"tool_versions": {
|
| 217 |
"qairt": "2.50.0.260828221209"
|
| 218 |
},
|
| 219 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_sa7255p.zip"
|
| 220 |
}
|
| 221 |
},
|
| 222 |
"qualcomm-sa8775p": {
|
|
|
|
| 224 |
"tool_versions": {
|
| 225 |
"qairt": "2.50.0.260828221209"
|
| 226 |
},
|
| 227 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_sa8775p.zip"
|
| 228 |
}
|
| 229 |
},
|
| 230 |
"qualcomm-snapdragon-8-elite-for-galaxy": {
|
|
|
|
| 233 |
"qairt": "2.50.0.260828221209",
|
| 234 |
"onnx_runtime": "1.30.0"
|
| 235 |
},
|
| 236 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_8_elite_for_galaxy.zip"
|
| 237 |
},
|
| 238 |
"qnn_context_binary": {
|
| 239 |
"tool_versions": {
|
| 240 |
"qairt": "2.50.0.260828221209"
|
| 241 |
},
|
| 242 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_8_elite_for_galaxy.zip"
|
| 243 |
}
|
| 244 |
},
|
| 245 |
"qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
|
|
|
|
| 248 |
"qairt": "2.50.0.260828221209",
|
| 249 |
"onnx_runtime": "1.30.0"
|
| 250 |
},
|
| 251 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
|
| 252 |
},
|
| 253 |
"qnn_context_binary": {
|
| 254 |
"tool_versions": {
|
| 255 |
"qairt": "2.50.0.260828221209"
|
| 256 |
},
|
| 257 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
|
| 258 |
}
|
| 259 |
},
|
| 260 |
"qualcomm-snapdragon-8gen3": {
|
|
|
|
| 263 |
"qairt": "2.50.0.260828221209",
|
| 264 |
"onnx_runtime": "1.30.0"
|
| 265 |
},
|
| 266 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_8gen3.zip"
|
| 267 |
},
|
| 268 |
"qnn_context_binary": {
|
| 269 |
"tool_versions": {
|
| 270 |
"qairt": "2.50.0.260828221209"
|
| 271 |
},
|
| 272 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_8gen3.zip"
|
| 273 |
}
|
| 274 |
},
|
| 275 |
"qualcomm-snapdragon-x-elite": {
|
|
|
|
| 278 |
"qairt": "2.50.0.260828221209",
|
| 279 |
"onnx_runtime": "1.30.0"
|
| 280 |
},
|
| 281 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_x_elite.zip"
|
| 282 |
},
|
| 283 |
"qnn_context_binary": {
|
| 284 |
"tool_versions": {
|
| 285 |
"qairt": "2.50.0.260828221209"
|
| 286 |
},
|
| 287 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_x_elite.zip"
|
| 288 |
}
|
| 289 |
},
|
| 290 |
"qualcomm-snapdragon-x2-elite": {
|
|
|
|
| 293 |
"qairt": "2.50.0.260828221209",
|
| 294 |
"onnx_runtime": "1.30.0"
|
| 295 |
},
|
| 296 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-precompiled_qnn_onnx-mixed-qualcomm_snapdragon_x2_elite.zip"
|
| 297 |
},
|
| 298 |
"qnn_context_binary": {
|
| 299 |
"tool_versions": {
|
| 300 |
"qairt": "2.50.0.260828221209"
|
| 301 |
},
|
| 302 |
+
"download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/zipformer/releases/v0.66.0/zipformer-qnn_context_binary-mixed-qualcomm_snapdragon_x2_elite.zip"
|
| 303 |
}
|
| 304 |
}
|
| 305 |
}
|