faster-whisper
CTranslate2-based Whisper with 4x faster transcription
About
faster-whisper is a reimplementation of OpenAI Whisper using CTranslate2, a Transformer inference engine that produces transcripts up to four times faster than openai-whisper at the same accuracy while using less memory. Further speedups are available via 8-bit quantization on CPU or GPU. Audio decoding uses PyAV, so an external FFmpeg install is not required. Maintained by SYSTRAN, released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Audio & Speech
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Added
- Jan 29, 2026
Related Tools
Free text-to-speech generator with multiple voices, accents, and languages. No signup required.
Transformer-based text-to-audio model from Suno
Deep learning toolkit for text-to-speech synthesis
OpenAI's powerful speech recognition model
Whisper with word-level timestamps and speaker diarization
Fast, local neural text-to-speech for home automation