SYSTRAN/faster-whisper

Health v2 · maintenance only

Adoption not part of the score

25104 stars · 2045 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A fast reimplementation of OpenAI's Whisper speech-to-text model built on the CTranslate2 inference engine, offering up to 4x speedup and lower memory usage than the original. It supports 8-bit quantization on both CPU and GPU and requires no system FFmpeg installation.

Use cases

• transcribe audio files to text
• convert speech to text in python
• faster whisper transcription
• run whisper on cpu with low memory
• batch transcribe long audio recordings
• subtitle generation from audio
• deploy speech-to-text on gpu efficiently

When to choose

• you need faster and more memory-efficient Whisper inference than openai/whisper
• you want int8 quantization for CPU or GPU deployment
• you want a pip-installable Python library without system FFmpeg dependencies
• you need batched transcription for throughput

When to avoid

• you need a non-Python runtime such as C++ or a single-file binary (consider whisper.cpp)
• you need features beyond transcription like training or fine-tuning Whisper
• you need streaming real-time ASR with low-latency partial results

Facets

library · maturity active

speech-recognition llm-inference machine-learning deep-learning speech-processing machine-learning python cross-platform whisper ctranslate2 speech-to-text transcription quantization int8 asr audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="SYSTRAN/faster-whisper")