Whisper Small is OpenAI's 244M-parameter multilingual Whisper checkpoint. It uses the standard Whisper encoder-decoder architecture for automatic speech recognition and speech translation, trained with large-scale weak supervision on 680k hours of labelled speech. Compared with larger Whisper checkpoints, the small model is easier to run locally while retaining the broad zero-shot behavior that makes Whisper useful across noisy datasets and domains. This OpenASR repo repackages the original openai/whisper-small weights as .oasr packs that run natively in the OpenASR runtime with no Python at inference time. For most users the q8_0 build is the recommended default; q4_k is for tighter memory budgets and fp16 is for verification or maximum fidelity.