中文
Libraries & frameworks

faster-whisper

SYSTRAN/faster-whisper

A faster Whisper speech transcription library built on CTranslate2 with a Python interface, using less memory than the original while supporting CPU/GPU execution and quantized inference for transcription workloads.

Topics

  • deep-learning
  • inference
  • openai
  • quantization
  • speech-recognition
  • speech-to-text
  • transformer
  • whisper