菜单
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. Supports standard and distilled models with word-level timestamps.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill faster-whisper命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
| name | faster-whisper |
| description | Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. Supports standard and distilled models with word-level timestamps. |
| version | 1.0.4 |
| author | ThePlasmak |
| homepage | https://github.com/ThePlasmak/faster-whisper |
| tags | ["audio","transcription","whisper","speech-to-text","ml","cuda","gpu"] |
| platforms | ["windows","linux","macos","wsl2"] |
| metadata | {"moltbot":{"emoji":"🗣️","requires":{"bins":["ffmpeg","python3"]}}} |
Local speech-to-text using faster-whisper — a CTranslate2 reimplementation of OpenAI's Whisper that runs 4-6x faster with identical accuracy. With GPU acceleration, expect ~20x realtime transcription (a 10-minute audio file in ~30 seconds).
Use this skill when you need to:
Trigger phrases: "transcribe this audio", "convert speech to text", "what did they say", "make a transcript", "audio to text", "subtitle this video"
When NOT to use:
| Task | Command | Notes |
|---|---|---|
| Basic transcription | ./scripts/transcribe audio.mp3 | Uses default distil-large-v3 |
| Faster English | ./scripts/transcribe audio.mp3 --model distil-medium.en --language en | English-only, 6.8x faster |
| Maximum accuracy | ./scripts/transcribe audio.mp3 --model large-v3-turbo --beam-size 10 | Slower but best quality |
| Word timestamps | ./scripts/transcribe audio.mp3 --word-timestamps | For subtitles/captions |
| JSON output | ./scripts/transcribe audio.mp3 --json -o output.json | Programmatic access |
| Multilingual | ./scripts/transcribe audio.mp3 --model large-v3-turbo | Auto-detects language |
基于 SOC 职业分类
| Remove silence |
./scripts/transcribe audio.mp3 --vad |
| Voice activity detection |
Choose the right model for your needs:
digraph model_selection {
rankdir=LR;
node [shape=box, style=rounded];
start [label="Start", shape=doublecircle];
need_accuracy [label="Need maximum\naccuracy?", shape=diamond];
multilingual [label="Multilingual\ncontent?", shape=diamond];
resource_constrained [label="Resource\nconstraints?", shape=diamond];
large_v3 [label="large-v3\nor\nlarge-v3-turbo", style="rounded,filled", fillcolor=lightblue];
large_turbo [label="large-v3-turbo", style="rounded,filled", fillcolor=lightblue];
distil_large [label="distil-large-v3\n(default)", style="rounded,filled", fillcolor=lightgreen];
distil_medium [label="distil-medium.en", style="rounded,filled", fillcolor=lightyellow];
distil_small [label="distil-small.en", style="rounded,filled", fillcolor=lightyellow];
start -> need_accuracy;
need_accuracy -> large_v3 [label="yes"];
need_accuracy -> multilingual [label="no"];
multilingual -> large_turbo [label="yes"];
multilingual -> resource_constrained [label="no (English)"];
resource_constrained -> distil_small [label="mobile/edge"];
resource_constrained -> distil_medium [label="some limits"];
resource_constrained -> distil_large [label="no"];
}
| Model | Size | Speed | Accuracy | Use Case |
|---|---|---|---|---|
tiny / tiny.en | 39M | Fastest | Basic | Quick drafts |
base / base.en | 74M | Very fast | Good | General use |
small / small.en | 244M | Fast | Better | Most tasks |
medium / medium.en | 769M | Moderate | High | Quality transcription |
large-v1/v2/v3 | 1.5GB | Slower | Best | Maximum accuracy |
large-v3-turbo | 809M | Fast | Excellent | Recommended for accuracy |
| Model | Size | Speed vs Standard | Accuracy | Use Case |
|---|---|---|---|---|
distil-large-v3 | 756M | ~6.3x faster | 9.7% WER | Default, best balance |
distil-large-v2 | 756M | ~5.8x faster | 10.1% WER | Fallback |
distil-medium.en | 394M | ~6.8x faster | 11.1% WER | English-only, resource-constrained |
distil-small.en | 166M | ~5.6x faster | 12.1% WER | Mobile/edge devices |
.en models are English-only and slightly faster/better for English content.
# Run the setup script (creates venv, installs deps, auto-detects GPU)
./setup.sh
# Run from PowerShell (auto-installs Python & ffmpeg if missing via winget)
.\setup.ps1
The Windows setup script will:
Requirements:
| Platform | Acceleration | Speed | Auto-Install |
|---|---|---|---|
| Windows + NVIDIA GPU | CUDA | ~20x realtime 🚀 | ✅ Full |
| Linux + NVIDIA GPU | CUDA | ~20x realtime 🚀 | Manual prereqs |
| WSL2 + NVIDIA GPU | CUDA | ~20x realtime 🚀 | Manual prereqs |
| macOS Apple Silicon | CPU* | ~3-5x realtime | Manual prereqs |
| macOS Intel | CPU | ~1-2x realtime | Manual prereqs |
| Windows (no GPU) | CPU | ~1x realtime | ✅ Full |
| Linux (no GPU) | CPU | ~1x realtime | Manual prereqs |
*faster-whisper uses CTranslate2 which is CPU-only on macOS, but Apple Silicon is fast enough for practical use.
The setup script auto-detects your GPU and installs PyTorch with CUDA. Always use GPU if available — CPU transcription is extremely slow.
| Hardware | Speed | 9-min video |
|---|---|---|
| RTX 3070 (GPU) | ~20x realtime | ~27 sec |
| CPU (int8) | ~0.3x realtime | ~30 min |
If setup didn't detect your GPU, manually install PyTorch with CUDA:
Linux/macOS/WSL2:
# For CUDA 12.x
uv pip install --python .venv/bin/python torch --index-url https://download.pytorch.org/whl/cu121
# For CUDA 11.x
uv pip install --python .venv/bin/python torch --index-url https://download.pytorch.org/whl/cu118
Windows:
# For CUDA 12.x
.venv\Scripts\pip install torch --index-url https://download.pytorch.org/whl/cu121
# For CUDA 11.x
.venv\Scripts\pip install torch --index-url https://download.pytorch.org/whl/cu118
Linux/macOS/WSL2:
# Basic transcription
./scripts/transcribe audio.mp3
# With specific model
./scripts/transcribe audio.wav --model large-v3-turbo
# With word timestamps
./scripts/transcribe audio.mp3 --word-timestamps
# Specify language (faster than auto-detect)
./scripts/transcribe audio.mp3 --language en
# JSON output
./scripts/transcribe audio.mp3 --json
Windows (cmd or PowerShell):
# Basic transcription
.\scripts\transcribe.cmd audio.mp3
# With specific model
.\scripts\transcribe.cmd audio.wav --model large-v3-turbo
# With word timestamps (PowerShell native syntax also works)
.\scripts\transcribe.ps1 audio.mp3 -WordTimestamps
# JSON output
.\scripts\transcribe.cmd audio.mp3 --json
--model, -m Model name (default: distil-large-v3)
--language, -l Language code (e.g., en, es, fr - auto-detect if omitted)
--word-timestamps Include word-level timestamps
--beam-size Beam search size (default: 5, higher = more accurate but slower)
--vad Enable voice activity detection (removes silence)
--json, -j Output as JSON
--output, -o Save transcript to file
--device cpu or cuda (auto-detected)
--compute-type int8, float16, float32 (default: auto-optimized)
--quiet, -q Suppress progress messages
# Transcribe YouTube audio (after extraction with yt-dlp)
yt-dlp -x --audio-format mp3 <URL> -o audio.mp3
./scripts/transcribe audio.mp3
# Batch transcription with JSON output
for file in *.mp3; do
./scripts/transcribe "$file" --json > "${file%.mp3}.json"
done
# High-accuracy transcription with larger beam size
./scripts/transcribe audio.mp3 \
--model large-v3-turbo --beam-size 10 --word-timestamps
# Fast English-only transcription
./scripts/transcribe audio.mp3 \
--model distil-medium.en --language en
# Transcribe with VAD (removes silence)
./scripts/transcribe audio.mp3 --vad
| Mistake | Problem | Solution |
|---|---|---|
| Using CPU when GPU available | 10-20x slower transcription | Check nvidia-smi on Windows/Linux; verify CUDA installation |
| Not specifying language | Wastes time auto-detecting on known content | Use --language en when you know the language |
| Using wrong model | Unnecessary slowness or poor accuracy | Default distil-large-v3 is excellent; only use large-v3 if accuracy issues |
| Ignoring distilled models | Missing 6x speedup with <1% accuracy loss | Try distil-large-v3 before reaching for standard models |
| Forgetting ffmpeg | Setup fails or audio can't be processed | Setup script handles this; manual installs need ffmpeg separately |
| Out of memory errors | Model too large for available VRAM/RAM | Use smaller model or --compute-type int8 |
| Over-engineering beam size | Diminishing returns past beam-size 5-7 | Default 5 is fine; try 10 for critical transcripts |
~/.cache/huggingface/ (one-time)distil-large-v3: ~2GB RAM / ~1GB VRAMlarge-v3-turbo: ~4GB RAM / ~2GB VRAMtiny/base: <1GB RAM"CUDA not available — using CPU": Install PyTorch with CUDA (see GPU Support above)
Setup fails: Make sure Python 3.10+ is installed
Out of memory: Use smaller model or --compute-type int8
Slow on CPU: Expected — use GPU for practical transcription
Model download fails: Check ~/.cache/huggingface/ permissions (Linux/macOS) or %USERPROFILE%\.cache\huggingface\ (Windows)
"winget not found": Install App Installer from Microsoft Store, or install Python/ffmpeg manually
"Python not in PATH after install": Close and reopen your terminal, then run setup.ps1 again
PowerShell execution policy error: Run Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned or use transcribe.cmd instead
nvidia-smi not found but have GPU: Install NVIDIA drivers — the Game Ready or Studio drivers include nvidia-smi