# Send Faster Whisper Gpu to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "faster-whisper-gpu",
    "name": "Faster Whisper Gpu",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/FelipeOFF/faster-whisper-gpu",
    "canonicalUrl": "https://clawhub.ai/FelipeOFF/faster-whisper-gpu",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/faster-whisper-gpu",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=faster-whisper-gpu",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "EXAMPLES.md",
      "README.md",
      "SKILL.md",
      "requirements.txt",
      "transcribe.py"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "faster-whisper-gpu",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T10:53:04.776Z",
      "expiresAt": "2026-05-08T10:53:04.776Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=faster-whisper-gpu",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=faster-whisper-gpu",
        "contentDisposition": "attachment; filename=\"faster-whisper-gpu-0.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "faster-whisper-gpu"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/faster-whisper-gpu"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/faster-whisper-gpu",
    "downloadUrl": "https://openagent3.xyz/downloads/faster-whisper-gpu",
    "agentUrl": "https://openagent3.xyz/skills/faster-whisper-gpu/agent",
    "manifestUrl": "https://openagent3.xyz/skills/faster-whisper-gpu/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/faster-whisper-gpu/agent.md"
  }
}
```
## Documentation

### 🎙️ Faster Whisper GPU

High-performance local speech-to-text transcription using Faster Whisper with NVIDIA GPU acceleration.

### ✨ Features

🚀 GPU Accelerated: Uses NVIDIA CUDA for blazing-fast transcription
🔒 100% Local: No data leaves your machine. Complete privacy.
💰 Free Forever: No API costs. Run unlimited transcriptions.
🌍 Multilingual: Supports 99 languages with automatic detection
📁 Multiple Formats: Input: MP3, WAV, FLAC, OGG, M4A. Output: TXT, SRT, JSON
🎯 Multiple Models: From tiny (fast) to large-v3 (most accurate)
🎬 Subtitle Generation: Create SRT files with word-level timestamps

### Hardware

NVIDIA GPU with CUDA support (recommended: 4GB+ VRAM)
Or CPU-only mode (slower but works on any machine)

### Software

Python 3.8+
NVIDIA drivers (for GPU support)
CUDA Toolkit 11.8+ or 12.x

### Installation

# Install dependencies
pip install faster-whisper torch

# Verify GPU is available
python -c "import torch; print(f'CUDA available: {torch.cuda.is_available()}')"

### Basic Usage

# Transcribe an audio file (auto-detects GPU)
python transcribe.py audio.mp3

# Specify language explicitly
python transcribe.py audio.mp3 --language pt

# Output as SRT subtitles
python transcribe.py audio.mp3 --format srt --output subtitles.srt

# Use larger model for better accuracy
python transcribe.py audio.mp3 --model large-v3

### Command Line Options

python transcribe.py <audio_file> [options]

Options:
  --model {tiny,base,small,medium,large-v1,large-v2,large-v3}
                        Model size to use (default: base)
  --language LANG       Language code (e.g., 'pt', 'en', 'es'). Auto-detect if not specified.
  --format {txt,srt,json,vtt}
                        Output format (default: txt)
  --output FILE         Output file path (default: stdout)
  --device {cuda,cpu}   Device to use (default: cuda if available)
  --compute_type {int8,int8_float16,int16,float16,float32}
                        Computation precision (default: float16)
  --task {transcribe,translate}
                        Task: transcribe or translate to English (default: transcribe)
  --vad_filter          Enable voice activity detection filter
  --vad_parameters MIN_DURATION_ON,MIN_DURATION_OFF
                        VAD parameters as comma-separated values
  --condition_on_previous_text
                        Condition on previous text (default: True)
  --initial_prompt PROMPT
                        Initial prompt to guide transcription
  --word_timestamps     Include word-level timestamps (for SRT/JSON)
  --hotwords WORDS      Comma-separated hotwords to boost recognition

### Examples

Portuguese Transcription with SRT Output

python transcribe.py meeting.mp3 --language pt --format srt --output meeting.srt

English Translation from Any Language

python transcribe.py japanese_audio.mp3 --task translate --format txt

High-Accuracy Mode with Large Model

python transcribe.py podcast.mp3 --model large-v3 --vad_filter --word_timestamps

CPU-Only Mode (no GPU)

python transcribe.py audio.mp3 --device cpu --compute_type int8

### 🐍 Python API

from faster_whisper import WhisperModel

# Load model
model = WhisperModel("base", device="cuda", compute_type="float16")

# Transcribe
segments, info = model.transcribe("audio.mp3", language="pt")

print(f"Detected language: {info.language} (probability: {info.language_probability:.2f})")

for segment in segments:
    print(f"[{segment.start:.2f}s -> {segment.end:.2f}s] {segment.text}")

### 📊 Model Sizes & VRAM Requirements

ModelParametersVRAM RequiredRelative SpeedAccuracytiny39 M~1 GB~32xBasicbase74 M~1 GB~16xGoodsmall244 M~2 GB~6xBettermedium769 M~5 GB~2xGreatlarge-v31550 M~10 GB1xBest

Benchmarks measured on NVIDIA RTX 4090

### 🔍 Supported Languages

Faster Whisper supports 99 languages including:

Portuguese (pt)
English (en)
Spanish (es)
French (fr)
German (de)
Italian (it)
Japanese (ja)
Chinese (zh)
Russian (ru)
And 90+ more...

### CUDA Out of Memory

# Use smaller model
python transcribe.py audio.mp3 --model tiny

# Or use CPU
python transcribe.py audio.mp3 --device cpu

# Or reduce precision
python transcribe.py audio.mp3 --compute_type int8

### Model Download Issues

Models are automatically downloaded on first use to ~/.cache/huggingface/hub/.
If behind a proxy, set:

export HF_HOME=/path/to/custom/cache

### Slow Transcription

Ensure GPU is being used: check nvidia-smi during transcription
Use smaller model for faster results
Enable VAD filter to skip silent parts

### 🤝 Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Submit a pull request

### 📜 License

MIT License - See LICENSE for details.

Faster Whisper is developed by SYSTRAN and based on OpenAI's Whisper.

### 🙏 Acknowledgments

OpenAI Whisper - Original model
Faster Whisper - Optimized implementation
CTranslate2 - Fast inference engine

Made with ❤️ for the OpenClaw community
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: FelipeOFF
- Version: 0.1.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-01T10:53:04.776Z
- Expires at: 2026-05-08T10:53:04.776Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/faster-whisper-gpu)
- [Send to Agent page](https://openagent3.xyz/skills/faster-whisper-gpu/agent)
- [JSON manifest](https://openagent3.xyz/skills/faster-whisper-gpu/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/faster-whisper-gpu/agent.md)
- [Download page](https://openagent3.xyz/downloads/faster-whisper-gpu)