This is a conversion of OpenAI's Whisper large-v2 model to the CTranslate2 format for faster inference. It supports automatic speech recognition in 99 languages and can be used through the faster-whisper Python package. The model is provided in FP16 precision and is suitable for local transcription tasks.
In the Voice, TTS & speech space, Faster Whisper Large takes a focused approach. It focuses on running high-accuracy, multilingual speech-to-text locally with significantly improved inference speed. It is built as an open-source project for developers. Faster Whisper Large is open source under the Open Source license. The product ships for the web and API.
It is developed by Systran, and the product first shipped in 2022. Key capabilities include Speech Recognition, CTranslate2 Format, and Multi-Language Support.
Latest indexed changes and source events
Systran/faster-whisper-large-v2 verified by the PulseGate indexer
