v0.58.0

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

README.md

@@ -15,7 +15,7 @@ pipeline_tag: automatic-speech-recognition
 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.
 
 This is based on the implementation of Whisper-Small found [here](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper).
-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/v0.57.3/src/qai_hub_models/models/whisper_small) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
+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/v0.58.0/src/qai_hub_models/models/whisper_small) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
 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.
 
@@ -31,39 +31,39 @@ Below are pre-exported model assets ready for deployment.
 
 | Runtime | Precision | Chipset | SDK Versions | Download |
 |---|---|---|---|---|
-| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
-| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
-| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
-| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
-| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
-| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
-| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
-| PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
-| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
-| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
-| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
-| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
-| QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
-| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip)
-| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
-| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
-| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip)
-| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip)
-| QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip)
+| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
+| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
+| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
+| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
+| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
+| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
+| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
+| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
+| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
+| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
+| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
+| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
+| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
+| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip)
+| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
+| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
+| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip)
+| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip)
+| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip)
 
 For more device-specific assets and performance metrics, visit **[Whisper-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_small)**.
 
 
 ### Option 2: Export with Custom Configurations
 
-Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/whisper_small) Python library to compile and export the model with your own:
+Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/whisper_small) Python library to compile and export the model with your own:
 - Custom weights (e.g., fine-tuned checkpoints)
 - Custom input shapes
 - Target device and runtime configurations
 
 This option is ideal if you need to customize the model beyond the default configuration provided here.
 
-See our repository for [Whisper-Small on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/whisper_small) for usage instructions.
+See our repository for [Whisper-Small on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/whisper_small) for usage instructions.
 
 ## Model Details
 
@@ -81,56 +81,96 @@ See our repository for [Whisper-Small on GitHub](https://github.com/qualcomm/ai-
 ## Performance Summary
 | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
 |---|---|---|---|---|---|---
-| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 6.645 ms | 60 - 60 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 10.07 ms | 287 - 287 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.84 ms | 75 - 87 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 18.347 ms | 75 - 89 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 12.343 ms | 62 - 64 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 18.347 ms | 75 - 89 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.439 ms | 43 - 51 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 13.697 ms | 60 - 122 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 8.428 ms | 58 - 70 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8750 | 8.428 ms | 58 - 70 MB | NPU
-| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS7181 | 10.07 ms | 287 - 287 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 6.755 ms | 60 - 60 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 9.812 ms | 287 - 287 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 10.101 ms | 75 - 87 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 17.898 ms | 74 - 89 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.235 ms | 0 - 318 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 17.898 ms | 74 - 89 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.385 ms | 43 - 55 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 13.586 ms | 60 - 122 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 8.354 ms | 58 - 71 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 8.354 ms | 58 - 71 MB | NPU
+| decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.812 ms | 287 - 287 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 7.088 ms | 60 - 60 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 10.172 ms | 60 - 60 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 9.695 ms | 36 - 44 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 17.665 ms | 60 - 75 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 | 19.253 ms | 48 - 56 MB | NPU
-| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 12.074 ms | 58 - 60 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.074 ms | 58 - 60 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 13.564 ms | 45 - 53 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 13.564 ms | 45 - 53 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 13.564 ms | 45 - 53 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 17.665 ms | 60 - 75 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.365 ms | 1 - 10 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 13.422 ms | 60 - 128 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 19.253 ms | 48 - 56 MB | NPU
-| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 13.422 ms | 60 - 128 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 8.371 ms | 7 - 20 MB | NPU
 | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 14.617 ms | 58 - 63 MB | NPU
-| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8750 | 8.371 ms | 7 - 20 MB | NPU
-| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS7181 | 10.172 ms | 60 - 60 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 59.819 ms | 132 - 132 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 133.381 ms | 255 - 255 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 97.509 ms | 107 - 113 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 273.643 ms | 125 - 140 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 131.724 ms | 0 - 258 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 273.643 ms | 125 - 140 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.601 ms | 127 - 138 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 155.305 ms | 127 - 130 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 70.427 ms | 111 - 123 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8750 | 70.427 ms | 111 - 123 MB | NPU
-| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS7181 | 133.381 ms | 255 - 255 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 8.371 ms | 7 - 20 MB | NPU
+| decoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.172 ms | 60 - 60 MB | NPU
+| decoder | VOICE_AI | float | Snapdragon® X2 Elite | 6.992 ms | 60 - 60 MB | NPU
+| decoder | VOICE_AI | float | Snapdragon® X Elite | 10.671 ms | 60 - 60 MB | NPU
+| decoder | VOICE_AI | float | Snapdragon® 8 Gen 3 Mobile | 9.95 ms | 70 - 79 MB | NPU
+| decoder | VOICE_AI | float | Snapdragon® 8 Gen 1 Mobile | 17.681 ms | 40 - 49 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® QCS8275 | 18.938 ms | 49 - 57 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.259 ms | 36 - 40 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® SA8775P | 14.141 ms | 50 - 58 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® SA8650P | 14.141 ms | 50 - 58 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® SA8255P | 14.141 ms | 50 - 58 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® QCS8450 | 17.681 ms | 40 - 49 MB | NPU
+| decoder | VOICE_AI | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.363 ms | 45 - 54 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® Dragonwing™ IQ-9075 | 13.417 ms | 60 - 128 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® SA7255P | 18.938 ms | 49 - 57 MB | NPU
+| decoder | VOICE_AI | float | Snapdragon® 8 Elite Mobile | 8.38 ms | 0 - 9 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® SA8295P | 14.575 ms | 58 - 63 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® Dragonwing™ Q-8750 | 8.38 ms | 0 - 9 MB | NPU
+| decoder | VOICE_AI | float | Qualcomm® Dragonwing™ IQ-X7181 | 10.671 ms | 60 - 60 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 60.049 ms | 133 - 133 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 132.403 ms | 255 - 255 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 98.329 ms | 126 - 139 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 275.168 ms | 125 - 139 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 129.91 ms | 3 - 261 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 275.168 ms | 125 - 139 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.831 ms | 127 - 141 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 155.706 ms | 127 - 131 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 70.112 ms | 129 - 141 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 70.112 ms | 129 - 141 MB | NPU
+| encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 132.403 ms | 255 - 255 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 60.168 ms | 0 - 0 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 132.887 ms | 0 - 0 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 97.198 ms | 17 - 24 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 270.612 ms | 0 - 13 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 | 449.261 ms | 0 - 8 MB | NPU
-| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 130.318 ms | 0 - 3 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 130.318 ms | 0 - 3 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 155.191 ms | 1 - 10 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 155.191 ms | 1 - 10 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 155.191 ms | 1 - 10 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 270.612 ms | 0 - 13 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 58.128 ms | 1 - 9 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 154.733 ms | 0 - 55 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 449.261 ms | 0 - 8 MB | NPU
-| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 154.733 ms | 0 - 55 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 70.132 ms | 1 - 10 MB | NPU
 | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 200.172 ms | 1 - 6 MB | NPU
-| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8750 | 70.132 ms | 1 - 10 MB | NPU
-| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS7181 | 132.887 ms | 0 - 0 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 70.132 ms | 1 - 10 MB | NPU
+| encoder | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 132.887 ms | 0 - 0 MB | NPU
+| encoder | VOICE_AI | float | Snapdragon® X2 Elite | 60.507 ms | 0 - 0 MB | NPU
+| encoder | VOICE_AI | float | Snapdragon® X Elite | 132.283 ms | 0 - 0 MB | NPU
+| encoder | VOICE_AI | float | Snapdragon® 8 Gen 3 Mobile | 98.46 ms | 3 - 11 MB | NPU
+| encoder | VOICE_AI | float | Snapdragon® 8 Gen 1 Mobile | 274.748 ms | 0 - 9 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® QCS8275 | 449.416 ms | 1 - 8 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 129.513 ms | 0 - 5 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® SA8775P | 154.739 ms | 1 - 11 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® SA8650P | 154.739 ms | 1 - 11 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® SA8255P | 154.739 ms | 1 - 11 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® QCS8450 | 274.748 ms | 0 - 9 MB | NPU
+| encoder | VOICE_AI | float | Snapdragon® 8 Elite Gen 5 Mobile | 57.851 ms | 1 - 10 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® Dragonwing™ IQ-9075 | 155.191 ms | 0 - 55 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® SA7255P | 449.416 ms | 1 - 8 MB | NPU
+| encoder | VOICE_AI | float | Snapdragon® 8 Elite Mobile | 70.388 ms | 1 - 10 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® SA8295P | 199.937 ms | 1 - 6 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® Dragonwing™ Q-8750 | 70.388 ms | 1 - 10 MB | NPU
+| encoder | VOICE_AI | float | Qualcomm® Dragonwing™ IQ-X7181 | 132.283 ms | 0 - 0 MB | NPU
 
 ## License
 * The license for the original implementation of Whisper-Small can be found

release_assets.json

@@ -1,5 +1,5 @@
 {
-    "version": "0.57.3",
+    "version": "0.58.0",
     "precisions": {
         "float": {
             "chipset_assets": {
@@ -8,14 +8,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip"
                     }
                 },
                 "qualcomm-snapdragon-8gen3": {
@@ -23,14 +23,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip"
                     }
                 },
                 "qualcomm-snapdragon-8-elite-for-galaxy": {
@@ -38,14 +38,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip"
                     }
                 },
                 "qualcomm-snapdragon-8-elite-gen5-for-galaxy": {
@@ -53,14 +53,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip"
                     }
                 },
                 "qualcomm-snapdragon-x-elite": {
@@ -68,14 +68,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip"
                     }
                 },
                 "qualcomm-snapdragon-x2-elite": {
@@ -83,14 +83,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip"
                     }
                 },
                 "qualcomm-sa7255p": {
@@ -98,7 +98,7 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_sa7255p.zip"
                     }
                 },
                 "qualcomm-sa8295p": {
@@ -106,7 +106,7 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_sa8295p.zip"
                     }
                 },
                 "qualcomm-sa8775p": {
@@ -114,7 +114,7 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_sa8775p.zip"
                     }
                 },
                 "qualcomm-qcs8550-proxy": {
@@ -122,14 +122,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip"
                     }
                 },
                 "qualcomm-qcs9075": {
@@ -137,14 +137,14 @@
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-qnn_context_binary-float-qualcomm_qcs9075.zip"
                     },
                     "precompiled_qnn_onnx": {
                         "tool_versions": {
                             "qairt": "2.45.0.260326154327",
                             "onnx_runtime": "1.25.0"
                         },
-                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.57.3/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip"
+                        "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_small/releases/v0.58.0/whisper_small-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip"
                     }
                 }
             }