360 Secure SkillHub
360 安全技能中心

Faster Whisper Local

使用 faster-whisper 在本地将音频文件转写为文本。setup.sh 负责创建虚拟环境并安装依赖、自动检测 NVIDIA GPU；transcribe 脚本支持指定模型、词级时间戳、JSON 输出和 VAD 静音过滤。需要 Python 3.10 及以上与系统已安装的 ffmpeg。

jeminay
jeminay
热度 94.62
最近更新 2026-05-11 17:26:30
分类：效率依赖：代码执行 / 读写文件应用场景：文件转换

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add faster-whisper-local
Metadata
name
faster-whisper
description
Local speech-to-text using faster-whisper. High-performance transcription with GPU acceleration support. Includes word-level timestamps and distilled models. Use when asked to "transcribe audio", "whisper", or "speech to text".
metadata
{"openclaw":{"requires":{"bins":["ffmpeg","python3"],"pip":["faster-whisper","torch"]}}}

Faster-Whisper

High-performance local speech-to-text using faster-whisper.

Setup

1. Run Setup Script

Execute the setup script to create a virtual environment and install dependencies. It will automatically detect NVIDIA GPUs for CUDA acceleration.

./setup.sh

Requirements:

  • Python 3.10 or later
  • ffmpeg (installed on the system)

Usage

Use the transcription script to process audio files.

Basic Transcription

./scripts/transcribe audio.mp3

Advanced Options

  • Specific Model: ./scripts/transcribe audio.mp3 --model large-v3-turbo
  • Word Timestamps: ./scripts/transcribe audio.mp3 --word-timestamps
  • JSON Output: ./scripts/transcribe audio.mp3 --json
  • VAD (Silence Removal): ./scripts/transcribe audio.mp3 --vad

Available Models

  • distil-large-v3 (default): Best balance of speed and accuracy.
  • large-v3-turbo: Recommended for multilingual or highest accuracy tasks.
  • medium.en, small.en: Faster, English-only versions.

Troubleshooting

  • No GPU detected: Ensure NVIDIA drivers and CUDA are correctly installed. CPU transcription is significantly slower.
  • OOM Error: Use a smaller model (e.g., small or base) or use --compute-type int8.