This is a converted version of the Whisper large-v3-turbo model in MLX format, optimized for Apple silicon. It performs automatic speech recognition (ASR) by transcribing audio to text. The model can be used locally with the mlx-whisper library and is suitable for developers building transcription tools or voice interfaces.
Whisper Large V3 Turbo sits in PulseGate's Voice, TTS & speech category. It focuses on transcribing audio files efficiently on Apple silicon hardware using MLX. It is built as an open-source project for developers. Whisper Large V3 Turbo is open source under the Open Source license. Whisper Large V3 Turbo is available on the web, the command line, and API.
mlx-community builds and maintains Whisper Large V3 Turbo, and it first shipped in 2024. It operates in a well-populated space: PulseGate tracks 11 similar projects. Key capabilities include speech-to-text, MLX format, and quantized model.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do