whisper-large-v3-turbo

Model overview

whisper-large-v3-turbo is published by OpenAI as an automatic-speech-recognition model. The captured configuration identifies WhisperForConditionalGeneration with whisper model type, and Safetensors metadata reports 808,878,080 parameters. According to the model card, it is otherwise the same as large-v3 except for the reduced decoder depth.

Recorded capabilities

Use cases in the source record

• Speech-recognition transcription using the publisher-documented Transformers pipeline for arbitrary-length audio.
• Speech-translation experiments where the publisher describes multilingual recognition and translation behavior.
• Long-form transcription using the publisher-described sequential or chunked 30-second handling.

Limitations and unknowns

• According to the model card, predictions may hallucinate unspoken text, perform unevenly across languages and accents, and produce repetitive text; users should evaluate before deployment.
• No Ethen-measured evaluation results were extracted; only publisher-described behavior and limitations were captured.
• No context-window value was extracted from this record.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: openai/whisper-large-v3-turbo

Captured: Unknown. Processed: 2026-09-07T19:34:54.513580+00:00.

Whisper Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3 . In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation.…