ScriptsMar 31, 2026·2 min read

Faster Whisper — 4x Faster Speech-to-Text

Faster Whisper is a reimplementation of OpenAI Whisper using CTranslate2, up to 4x faster with less memory. 21.8K+ GitHub stars. GPU/CPU, 8-bit quantization, word timestamps, VAD. MIT licensed.

TO
TokRepo精选 · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

# Install
pip install faster-whisper

# Transcribe audio
python -c "
from faster_whisper import WhisperModel
model = WhisperModel('large-v3', device='cuda', compute_type='float16')
segments, info = model.transcribe('audio.mp3')
print(f'Language: {info.language} (prob {info.language_probability:.2f})')
for segment in segments:
    print(f'[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}')
"
Intro

Faster Whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, achieving up to 4x faster transcription with comparable accuracy and less memory usage. With 21,800+ GitHub stars and MIT license, it supports GPU and CPU execution, 8-bit quantization for efficiency, batched transcription, word-level timestamps, and Voice Activity Detection (VAD) filtering. On a 13-minute audio sample with the Large-v2 model, Faster Whisper completes in 1m03s vs OpenAI Whisper's 2m23s.

Best for: Developers needing fast, accurate speech-to-text transcription for audio/video processing Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf Models: All Whisper models + Distil-Whisper variants

Key Features

  • 4x faster: CTranslate2 engine dramatically reduces transcription time
  • Less memory: Lower VRAM usage than original Whisper implementation
  • 8-bit quantization: Further reduce memory with minimal accuracy loss
  • Word-level timestamps: Precise timing for each word in the transcript
  • VAD filtering: Skip silent sections using Silero VAD
  • Batched transcription: Process multiple audio segments in parallel
  • Distil-Whisper support: Compatible with smaller, faster distilled models

FAQ

Q: What is Faster Whisper? A: Faster Whisper is a CTranslate2 reimplementation of OpenAI Whisper with 21.8K+ stars. It runs up to 4x faster with less memory, supports 8-bit quantization, word timestamps, and VAD filtering. MIT licensed.

Q: How do I install Faster Whisper? A: Run pip install faster-whisper. Then use WhisperModel('large-v3') in Python to transcribe audio files with GPU or CPU.

🙏

Source & Thanks

Created by SYSTRAN. Licensed under MIT. SYSTRAN/faster-whisper — 21,800+ GitHub stars

Related Assets

Kokoro — Lightweight 82M TTS in 9 Languages

Kokoro is an 82M parameter text-to-speech model delivering quality comparable to larger models. 6.2K+ GitHub stars. Supports English, Spanish, French, Japanese, Chinese, and more. Apache 2.0.

TokRepo精选

GPT4All — Run LLMs Privately on Your Desktop

GPT4All runs large language models privately on everyday desktops and laptops without GPUs or API calls. 77.2K+ GitHub stars. Desktop app + Python SDK, LocalDocs for private data. MIT licensed.

TokRepo精选

vLLM — High-Throughput LLM Serving Engine

vLLM is a high-throughput and memory-efficient LLM inference engine. 74.8K+ GitHub stars. PagedAttention, continuous batching, OpenAI-compatible API, multi-GPU serving. Apache 2.0.

TokRepo精选
◈Home🏆Trending👤Me