Quantizing Whisper: How Design Choices Affect ASR Performance

Arthur Söhler, Julian Irigoyen, Andreas Søeborg Kirkedal


Abstract
Large speech recognition models like OpenAI’s Whisper achieve high accuracy but are difficult to deploy in resource-constrained environments due to their high memory and computational demands. This matters for low-resource and on-device settings, where compute and memory constraints often limit the practical use and evaluation of ASR systems. To address this, we present a unified, cross-library evaluation of post-training quantization (PTQ) on Whisper-small, comparing supported configurations across quantization scheme, method, granularity, and bit-width. Our study is based on four libraries—PyTorch, Optimum-Quanto, HQQ, and bitsandbytes. Experiments on LibriSpeech test-clean and test-other show that dynamic int8 quantization with Optimum-Quanto offers the best trade-off, reducing model size by 57% while lowering Word Error Rate below the baseline. Additional experiments on Whisper-base and Whisper-tiny confirm these trends, though with more pronounced degradation at lower bit-widths. Static quantization performed worse, likely due to the absence of efficient low-bit implementations for operations such as LayerNorm and Softmax. More aggressive formats (e.g., nf4, int3) achieved up to 71% compression at the cost of accuracy in acoustically challenging conditions. Our results demonstrate that carefully chosen PTQ methods can substantially reduce model size and inference cost without retraining, enabling efficient deployment of Whisper on constrained hardware.
Anthology ID:
2026.speakable-1.5
Volume:
Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Nina Hosseini-Kivanani, Alessio Brutti, Marco Matassoni, Sandipana Dowerah, Davide Liga, Christoph Schommer
Venues:
SPEAKABLE | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
39–46
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-speakable-05
DOI:
10.63317/4f2o9uqpxhn7
Bibkey:
Cite (ACL):
Arthur Söhler, Julian Irigoyen, and Andreas Søeborg Kirkedal. 2026. Quantizing Whisper: How Design Choices Affect ASR Performance. In Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026, pages 39–46, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Quantizing Whisper: How Design Choices Affect ASR Performance (Söhler et al., SPEAKABLE 2026)
Copy Citation: