Whisper‑Tiny‑En is the English‑only version of OpenAI’s Whisper tiny model, optimized specifically for speech recognition in English under resource‑constrained and real‑time deployment. Based on a Transformer encoder‑decoder architecture, it is trained on 680 k hours of English audio and delivers robust performance in noisy environments and on long‑form audio segments.

• It has approximately 39 M parameters using the tiny.en checkpoint, enabling fast inference.
• The model is well‑balanced in terms of performance and is suitable for deployment on mobile, edge, and web platforms, supporting applications like real‑time captioning, voice assistants, and speech‑driven control.

The source model can be found here

When the user has fine-tuned the source model, the model conversion process must be performed again.

Users can refer to either of the following two methods to complete the model conversion:

• Using AIMO for model conversion: Click Model Conversion Reference in the Performance Reference section on the right to view the conversion steps.

• Using Qualcomm QNN for model conversion: Please refer to the Qualcomm QNN Documentation.

The model performance benchmarks and example code provided by Model Farm are all implemented based on the APLUX AidLite SDK.

For models in .bin format, you can use either of the following two inference engines to run inference on Qualcomm chips:

Inference using APLUX AidLite: please refer to the APLUX AidLite Developer Documentation

Inference using Qualcomm QNN: Please refer to the Qualcomm QNN Documentation

Inference Example Code

The inference example code is implemented using the AidLite SDK.

Click Model & Code to download the model files and the inference code package. The file structure is as follows:

/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # aidlite python model inference example

    |__ cpp # aidlite cpp model inference example

    |__ README.md