Whisper‑Base‑En is the English-only base model in OpenAI’s Whisper series, featuring approximately 74 million parameters and optimized for efficient and accurate speech recognition in English. Compared to multilingual models, this English-specialized variant delivers lower error rates and faster inference under equivalent computational resources.

• Parameter Count: 74 million, offering about 7× faster inference compared to the large model.
• Training Data: Trained on roughly 680,000 hours of audio, including 438,000 hours of English-only speech.
• Architecture: Transformer encoder-decoder design, processing audio up to 30-second segments.
• Performance Highlights:
  • Achieves higher recognition accuracy than multilingual variants in English, especially under noisy conditions and accented speech.
  • Supports chunking, batching, and timestamp generation—ideal for real-time captions and transcription.
  • .en models show superior performance for English-only tasks, with noticeable gains at the tiny.en and base.en scale.

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