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.
Universal neural vocoder from NVIDIA that converts mel spectrograms into waveforms up to 44 kHz.
End-to-end Chinese and English spoken dialogue model from Zhipu AI with streaming speech output.
Audio foundation model unifying speech recognition, understanding, and conversation in one 7B model.
Python library for audio and music analysis, from spectrograms to beat tracking and features.
Deep learning toolkit for text-to-speech synthesis
Mentioned in
Building Real-Time Voice Agents: TEN, Pipecat, and LiveKit
A working guide to real-time voice agent stacks: latency budgets, turn detection, interruption handling,...
Max P
Beyond Whisper: Parakeet, SenseVoice and ASR in 2026
Whisper is no longer the default: how Parakeet, SenseVoice, Kimi-Audio, Ultravox and Moshi compare on...
Max P
whisper.cpp vs faster-whisper: Speed and Accuracy Compared
Two leading open source paths to running OpenAI Whisper. One is a CPU-friendly C/C++ port, the other rides...
Billy C