AIPython★ 26,758⑂ 2,244 forksMIT
SYSTRAN/faster-whisper
FAST SPEECH TRANSCRIPTION
Faster Whisper — an accelerated version of the Whisper model for speech recognition, built on CTranslate2. It supports quantized models and provides real‑time transcription on CPU and GPU.
// KEY FEATURES
- Transcribes audio files in real time using INT8 quantization via CTranslate2.
- Supports over 100 languages, including Russian and English, like the original Whisper.
- Accepts WAV, MP3 and streamed audio from microphone, returning text with timestamps.
- Provides Python‑API and CLI for batch transcription of large datasets.
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram