whisper-base-int8-litert

Whisper-base optimized for Arm-based mobile CPUs with SME2

Whisper-base automatic speech recognition optimized as an INT8 LiteRT .tflite model for Arm-based mobile CPUs with SME2.

Summary

This repository contains an Arm-optimized version of openai/whisper-base for automatic speech recognition. The model is provided in LiteRT .tflite (LiteRT runtime), targeting Mobile CPU systems.

This version is intended to demonstrate efficient inference on Arm-based platforms while preserving the original model's intended behavior. Arm has evaluated this model on librispeech_asr and measured performance on a representative evaluation target.

Key results

Original model

Model files

Performance

Performance was measured on the reference configuration below. Results are intended to make the optimization reproducible but do not guarantee identical performance on every Arm-based system.

Reference configuration

Performance results

Accuracy

Accuracy was evaluated using the same preprocessing, input resolution, and evaluation protocol described below. Where possible, the optimized model is compared against the original model under the same evaluation conditions.

Evaluation setup

Accuracy results

Accuracy was measured using the evaluation setup described above. Users should re-evaluate the model on their own data before production use.

Arm optimization approach

Arm optimized this model for efficient inference on Arm-based platforms using a hardware-aware conversion and validation flow.

For this release, Arm used:

The goal of this process is to improve deployment characteristics such as latency, memory use, model size, and runtime compatibility while preserving the model's intended behavior. Detailed conversion scripts, calibration configuration, or backend-specific implementation details may be provided separately where appropriate.

Using this model

Install dependencies

Dependencies are declared in pyproject.toml, which ships with this repository. Resolve and install them into a local virtual environment with uv:

uv python install
uv sync --frozen

Run the example

uv run example.py

Note: The Python/uv example runs on AWS Graviton (Ubuntu arm64) to confirm runtime compatibility only, and is intended as a guideline for building an equivalent run script on Mobile CPU systems.

Expected input

Expected output

Intended use

This model is intended for developers evaluating automatic speech recognition workloads on Arm-based platforms. It is suitable as a reference implementation for benchmarking, prototyping, and integration exploration.

Limitations

• Performance depends on the target device, runtime version, backend/delegate support, memory configuration, and system load.
• Accuracy was evaluated on LibriSpeech ASR test-clean and may not generalize to all domains.
• This release preserves the original model's intended task and behavior, but users should validate it for their own application, data, and deployment environment.
• This repository is not a replacement for the original model documentation.

Additional notes

• Quantization recipe: AI Edge Quantizer's dynamic_wi8_afp32 (TFLite hybrid quantization) — INT8 per-channel weights computed offline; activations are quantized to INT8 dynamically inside each kernel with a per-tensor scale computed on the fly, INT8 x INT8 to INT32 GEMM. Activation tensors are stored as FP32 on the graph edges between kernels — the "_afp32" in the recipe name refers to that storage, not to the arithmetic performed inside the kernel.
• The encoder and decoder are re-authored into separate exportable modules with explicit self-attention and cross-attention KV cache tensors, exported as the encode and decode signatures of a single .tflite file, so autoregressive decoding does not recompute the encoder or replay past attention state.
• Evaluated on the LibriSpeech test-clean split only; accuracy on test-other or noisier splits has not been measured.
• Fixed maximum of 128 generated tokens per utterance.
• Greedy decoding only, no beam search — transcriptions may differ from beam-search results reported elsewhere for Whisper-base.
• Evaluated only for English transcription (language forced to "en", task forced to "transcribe"); other languages and the translation task are untested.
• Latency and memory numbers are specific to the vivo X300; absolute numbers on other ARM chipsets, thread counts, or Android versions may differ.
• WER and CER are computed after Whisper-style text normalization on both reference and hypothesis transcripts, which affects the reported numeric values.
• Sample input: sample_input.flac is utterance 3570-5696-0000 of the LibriSpeech ASR corpus (test-clean split) by Panayotov et al., via OpenSLR (CC BY 4.0).

About this version

Original Model: openai/whisper-base 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.

Purpose of this Release

The Optimized Model is provided as a reference implementation to demonstrate and evaluate execution and performance on Arm-based systems. It is not a production-ready or supported solution.

Arm’s publication of the Optimized Model does not constitute an endorsement or certification of the Original Model or a representation that the Optimized Model is suitable for production use or any particular purpose.

To the fullest extent permitted by applicable law (i) the Optimized Model is provided “as is.” Arm makes no representations or warranties that the Original Model, the Optimized Model or their outputs are accurate, safe, secure, non-infringing, legally compliant, suitable for production use or fit for any particular purpose; and (ii) Arm will not be liable for any loss or damage arising from or in connection with the Optimized Model, its use or its outputs.

You are responsible for independently evaluating the Optimized Model, its outputs and its suitability for your intended use, including compliance with applicable legal, regulatory, safety and security requirements.

Arm does not commit to provide ongoing support, maintenance or updates for the Optimized Model. Any use of or reliance on the Optimized Model or its outputs is at your own risk.