mirror of
https://github.com/ThePlasmak/faster-whisper.git
synced 2026-09-19 07:38:23 +08:00
ThePlasmak
28b64fdcae
- setup.sh --check: replace full pyannote.audio import with importlib.util.find_spec + metadata version lookup; avoids 30-60s CUDA init, check now completes in ~12s - skill.json: move ffmpeg from requires.bins to optionalBins; ffmpeg not needed for basic transcription since PyAV handles decoding (only needed for --burn-in, --normalize, --denoise, --channel, --export-speakers) - CHANGELOG.md + SKILL.md: document both fixes
33 lines
599 B
JSON
33 lines
599 B
JSON
{
|
|
"name": "faster-whisper",
|
|
"version": "1.5.0",
|
|
"description": "Local speech-to-text using faster-whisper with 4-6x speed boost over OpenAI Whisper. GPU acceleration enables ~20x realtime transcription.",
|
|
"author": "ThePlasmak",
|
|
"tags": [
|
|
"whisper",
|
|
"transcription",
|
|
"speech-to-text",
|
|
"gpu",
|
|
"cuda",
|
|
"audio",
|
|
"ml"
|
|
],
|
|
"requires": {
|
|
"bins": [
|
|
"python3"
|
|
],
|
|
"optionalBins": [
|
|
"ffmpeg",
|
|
"yt-dlp"
|
|
],
|
|
"optionalPaths": [
|
|
"~/.cache/huggingface/token"
|
|
]
|
|
},
|
|
"platforms": [
|
|
"linux",
|
|
"macos",
|
|
"wsl2"
|
|
]
|
|
}
|