Whisper Medium INT8

Mobile CPUvivo X300SME2

INT8-quantized automatic speech recognition family for English speech-to-text, based on an encoder-decoder Transformer and optimized for efficient on-device use on ARM smartphones. It uses weight-only dynamic INT8 quantization with FP32 activations, LiteRT/TFLite execution, and KV-cache autoregressive decoding to reduce model size and improve transcription speed while preserving accuracy for clean English audio.View on Hugging Face

Accuracyvs base model

WER2.86%↓0.03 pp

CER1.26%↓0.01 pp

RTFx

1.45

Latency

8853.61 ms

Peak Memory

3150.16 MB

Get Started with this Model

Learning path

Transcribe speech with models from the Arm AI Portal on Android

Download and run Arm-optimized Whisper speech-to-text models from the Arm AI Portal on an Arm-powered Android device.

Recommended

Learning path

Build a Sentiment-Aware Voice Assistant with On-Device LLMs

Build an end-to-end, on-device voice assistant that understands both speech and emotion using Whisper, HuBERT, ONNX Runtime, and a local LLM with llama.cpp on Arm.

Model Evaluation

Base model: whisper-mediumTested on: vivo X300 (arm64, 8-core)

Evaluation Conditions

Automatic Speech Recognition · vivo X300 · INT8 · LibriSpeech (test-clean)

Metric	Resultsvs baseline	Change
End to end latency p50	8853.61ms174164.24ms	−165310.64 ms
End to end latency p90

About this version

Original Model:: whisper-medium by OpenAI — Repository
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to Apache-2.0.

This repository contains a converted or optimized version of the Original Model (the “Optimized Model”). The Original Model has been converted or optimized as described above for execution on Arm-based platforms.

No retraining or fine-tuning of the Original Model was performed as part of the conversion or optimization. The conversion or optimization was not intended to change the Original Model’s behavior or intended use.

Original Model and Documentation

For information about the Original Model, including its development, training data, intended uses, limitations and other relevant information, please refer to the Original Model repository. Information in that repository was provided by the original developer or other third parties and, unless expressly stated otherwise, has not been independently verified by Arm.

Licenses and Third-Party Terms

Use of the Original Model and the Optimized Model is subject to the applicable licenses, usage restrictions and other terms identified above and in the relevant repositories. Publication of the Optimized Model does not grant any rights beyond those provided under the applicable license terms.

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

Metric

Resultsvs baseline

Change

End to end latency p50

8853.61ms174164.24ms

−165310.64 ms

End to end latency p90

About this version

Original Model:: whisper-medium by OpenAI — Repository
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to Apache-2.0.

Original Model and Documentation

Licenses and Third-Party Terms

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

Configuration	Baseline	Arm Optimized
Dataset	LibriSpeech (test-clean)	LibriSpeech (test-clean)
Sample count	2,620	2,620
Batch size	1	1

Whisper Medium INT8

Get Started with this Model

Transcribe speech with models from the Arm AI Portal on Android

Build a Sentiment-Aware Voice Assistant with On-Device LLMs

Model Evaluation

Whisper Medium INT8

Get Started with this Model

Transcribe speech with models from the Arm AI Portal on Android

Build a Sentiment-Aware Voice Assistant with On-Device LLMs

Model Evaluation

Configuration

Comparability

Purpose of this Release