All builds for this model:

Whisper Medium is OpenAI's 769M-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. Medium delivers much of the large model's accuracy at a smaller footprint, a strong choice when quality matters but the largest checkpoint is too heavy. This OpenASR repo repackages the original openai/whisper-medium 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.

Converted from openai/whisper-medium with the OpenASR importer:

The .oasr container is GGUF-backed; packs use zero-copy mmap weight binding and graph buffer reuse to keep peak memory low.

These packs inherit the upstream model's license: Apache-2.0 (source). OpenASR packaging retains the upstream copyright and NOTICE; the only modifications are format conversion and quantization.

This pack is a redistribution of Whisper Medium, released by OpenAI (openai/whisper-medium). All credit for the original model, training recipe, and weights belongs to OpenAI. The upstream Hugging Face model card declares Apache-2.0 licensing; OpenASR only converts the weights into .oasr packages and adds quantized builds for local runtime use.