--- library_name: pytorch license: other tags: - foundation - android pipeline_tag: automatic-speech-recognition --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/web-assets/model_demo.png) # Whisper-Base: Optimized for Qualcomm Devices 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-Base 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/main/src/qai_hub_models/models/whisper_base) 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. ## Getting Started There are two ways to deploy this model on your device: ### Option 1: Download Pre-Exported Models Below are pre-exported model assets ready for deployment. | Runtime | Precision | Chipset | SDK Versions | Download | |---|---|---|---|---| | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-precompiled_qnn_onnx-float-qualcomm_qcs9075.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_base/releases/v0.51.0/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.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_base/releases/v0.51.0/whisper_base-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_base/releases/v0.51.0/whisper_base-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_base/releases/v0.51.0/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_8gen3.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_base/releases/v0.51.0/whisper_base-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_base/releases/v0.51.0/whisper_base-qnn_context_binary-float-qualcomm_sa8775p.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-qnn_context_binary-float-qualcomm_snapdragon_8_elite_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_base/releases/v0.51.0/whisper_base-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_base/releases/v0.51.0/whisper_base-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_base/releases/v0.51.0/whisper_base-qnn_context_binary-float-qualcomm_qcs9075.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/whisper_base/releases/v0.51.0/whisper_base-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip) For more device-specific assets and performance metrics, visit **[Whisper-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/whisper_base)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/whisper_base) 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-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/src/qai_hub_models/models/whisper_base) for usage instructions. ## Model Details **Model Type:** Model_use_case.speech_recognition **Model Stats:** - Model checkpoint: openai/whisper-base - Input resolution: 80x3000 (30 seconds audio) - Max decoded sequence length: 200 tokens - Number of parameters (encoder): 23.7M - Model size (encoder) (float): 90.7 MB - Number of parameters (decoder): 48.9M - Model size (decoder) (float): 187 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.48 ms | 20 - 31 MB | NPU | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 1.872 ms | 126 - 126 MB | NPU | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 3.618 ms | 125 - 125 MB | NPU | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.281 ms | 26 - 33 MB | NPU | decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 4.092 ms | 0 - 141 MB | NPU | decoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 4.615 ms | 20 - 43 MB | NPU | decoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.692 ms | 4 - 11 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.667 ms | 20 - 30 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 2.825 ms | 20 - 20 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 3.825 ms | 20 - 20 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 3.413 ms | 0 - 8 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 7.069 ms | 20 - 28 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 4.269 ms | 19 - 20 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 5.252 ms | 20 - 29 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 5.039 ms | 20 - 44 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 5.144 ms | 20 - 29 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 7.069 ms | 20 - 28 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 5.254 ms | 20 - 26 MB | NPU | decoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.826 ms | 0 - 13 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 14.952 ms | 38 - 48 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 15.796 ms | 65 - 65 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 37.209 ms | 67 - 67 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 27.432 ms | 38 - 46 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 36.53 ms | 7 - 56 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 44.62 ms | 41 - 44 MB | NPU | encoder | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 18.285 ms | 39 - 46 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 22.067 ms | 1 - 10 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 22.758 ms | 0 - 0 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 49.011 ms | 0 - 0 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 36.094 ms | 1 - 8 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 142.281 ms | 1 - 9 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 47.765 ms | 1 - 2 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 54.826 ms | 1 - 10 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 55.958 ms | 2 - 22 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 95.134 ms | 1 - 10 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 142.281 ms | 1 - 9 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 68.854 ms | 1 - 6 MB | NPU | encoder | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.513 ms | 1 - 10 MB | NPU ## License * The license for the original implementation of Whisper-Base can be found [here](https://github.com/huggingface/transformers/blob/v4.42.3/LICENSE). ## References * [Robust Speech Recognition via Large-Scale Weak Supervision](https://cdn.openai.com/papers/whisper.pdf) * [Source Model Implementation](https://github.com/huggingface/transformers/tree/v4.42.3/src/transformers/models/whisper) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).