ModelWhisper v3 / whisper-large-v3
Whisper large v3
An open-source speech recognition model released by OpenAI. It is the largest and highest-accuracy version in the Whisper series, with approximately 1.5 billion parameters. It supports transcription and translation across more than 90 languages, with strong performance on multilingual and accented speech.
Timeline (last 90 days)
Oct 12
The tool uses the Whisper large v3 model for speech recognition and handles the complete pipeline of downloading, audio extraction, segmentation, recognition, and timestamp alignment.
Unverified50%