SYSTRAN/faster-whisper
Faster Whisper transcription with CTranslate2
Reimplements OpenAI's Whisper using CTranslate2, a fast inference engine optimized for Transformer models, achieving up to 4× speedup with identical accuracy while reducing memory footprint. Supports 8-bit quantization for both CPU and GPU, batched inference for throughput optimization, and integrates with Hugging Face's distil-whisper checkpoints. Uses PyAV for audio decoding, eliminating external FFmpeg dependencies.
21,444 stars. Used by 24 other packages. Available on PyPI.
Stars
21,444
Forks
1,752
Language
Python
License
MIT
Category
Last pushed
Nov 19, 2025
Commits (30d)
0
Dependencies
6
Reverse dependents
24
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/SYSTRAN/faster-whisper"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
oseiskar/autosubsync
Automatically synchronize subtitles with audio using machine learning
YaoFANGUK/video-subtitle-extractor
视频硬字幕提取，生成srt文件。无需申请第三方API，本地实现文本识别。基于深度学习的视频字幕提取框架，包含字幕区域检测、字幕内容提取。A GUI tool for extracting...
machinelearningZH/audio-transcription
Transcribe any audio or video file. Edit and view your transcripts in a standalone HTML editor.
FL33TW00D/whisper-turbo
Cross-Platform, GPU Accelerated Whisper 🏎️
sanchit-gandhi/whisper-jax
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.