Back: Catalog

faster-whisper

Faster-whisper is a redesigned OpenAI Whisper model using the CTranslate2 inference engine. It runs up to 4 times faster using less memory while maintaining the same accuracy rate compared to the original Whisper model. Memory efficiency and processing speed can be increased using 8-bit quantization on both CPU and GPU.

FA

faster-whisper

95

SYSTRAN · AI Call Agents & Telephony

STARS26.3K
FORKS2.2K
COMMITS263
CONTRIBUTORS47
VERSIONv1.2.1
UPDATEDtoday
PythonCTranslate24-8x HızPipecat NativeMIT

Common commercial products in this category: Vapi, Bland AI, Retell AI

What can it do?
  • By applying 8-bit quantization on both CPU and GPU, you provide less memory consumption
  • You also decrypt audio files through the PyAV Python library, without installing FFmpeg on the system.
  • With word-level time stamps and a VAD filter, you write down audio files by extracting quiet sections.
User reviews
  • ↓ NegativeGitHub Issue

    Windows process crashes when the GPU model is unloaded

    “Thanks for your work first. It's useful. Howerver, there's still something wrong. It returns -1073740791 (0xC0000409) when dealing with a audio file in chinese. I have defined a function in which the variable 'result' is used to accept the 'segments' returned by the…”

  • • NeutralGitHub Issue

    Could not load library libcudnn_ops_infer.so.8

    “` Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory ` I'm using "nvidia/cuda:12.2.0-base-ubuntu20.04" image on google cloud with nvidia t4 gpus. The normal whisper package model works fine on…”

GitHub

Verified against README · Oct 26, 2026 · source

My note

Alternative pages

Vapi alternativesBland AI alternativesRetell AI alternatives

More in: AI Call Agents & Telephony