cstr/pyannote-v3-segmentation-gguf 3.0 GGUF - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.
Model Intelligence Sheet
cstr/pyannote-v3-segmentation-gguf overview
Native GGUF port of pyannote/segmentation-3.0 for speaker diarization.
Downloads
88
Likes
0
Pipeline
voice-activity-detection
Library
ggml
Visibility
Public
Access
Open
Repository Files & Downloads
1 files detected
Direct downloads for all repository files
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| pyannote-seg-3.0.gguf | GGUF | — | 5.70 MB | Download |
Model Details Live
Metadata Inspector
Normalized metadata (stored in metadata_json)
{
"metadata": {},
"card_data": {
"license": "mit",
"tags": [
"speaker-diarization",
"pyannote",
"gguf",
"crispasr"
],
"base_model": "pyannote/segmentation-3.0",
"pipeline_tag": "voice-activity-detection",
"library_name": "ggml",
"frontmatter": {
"license": "mit",
"tags": [
"speaker-diarization",
"pyannote",
"gguf",
"crispasr"
],
"base_model": "pyannote/segmentation-3.0",
"pipeline_tag": "voice-activity-detection",
"library_name": "ggml"
},
"hero_image_url": "",
"summary": "Native GGUF port of pyannote/segmentation-3.0 for speaker diarization.",
"quick_links": [],
"benchmark_table_html": "",
"readme_markdown": "---\nlicense: mit\ntags:\n - speaker-diarization\n - pyannote\n - gguf\n - crispasr\nbase_model: pyannote/segmentation-3.0\npipeline_tag: voice-activity-detection\nlibrary_name: ggml\n---\n\n# Pyannote Segmentation 3.0 — GGUF\n\nNative GGUF port of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) for speaker diarization.\n\n## Model details\n\n| Property | Value |\n|---|---|\n| Architecture | SincNet + 4× biLSTM + Linear + LogSoftmax |\n| Format | GGUF (F32) |\n| Size | 5.7 MB |\n| Tensors | 41 |\n| Output classes | 7 (powerset mapping → 3 speakers) |\n| Input | 10 s mono 16 kHz audio frames |\n\nThe model performs joint voice-activity detection, speaker segmentation, and overlapped-speech detection on short audio chunks. Downstream clustering then produces full-file speaker diarization.\n\n## Usage with CrispASR\n\n```bash\ncrispasr \\\n --diarize-method pyannote \\\n --sherpa-segment-model pyannote-seg-3.0.gguf \\\n audio.wav\n```\n\n## Provenance\n\nWeights were exported directly from the original PyTorch checkpoint (`pyannote/segmentation-3.0`) into GGUF format, preserving full F32 precision across all 41 tensors.\n\n## License\n\nMIT — same as the original pyannote-audio segmentation-3.0 model.\n",
"related_quantizations": []
},
"tags": [
"ggml",
"gguf",
"speaker-diarization",
"pyannote",
"crispasr",
"voice-activity-detection",
"base_model:pyannote/segmentation-3.0",
"base_model:quantized:pyannote/segmentation-3.0",
"license:mit",
"region:us"
],
"likes": 0,
"downloads": 88,
"gated": false,
"private": false,
"last_modified": "2026-04-12T14:07:28.000Z",
"created_at": "2026-04-12T14:06:43.000Z",
"pipeline_tag": "voice-activity-detection",
"library_name": "ggml"
}
Source payload excerpt (from Hugging Face API)
{
"_id": "69dba6f30a7d72741cbb3605",
"id": "cstr/pyannote-v3-segmentation-GGUF",
"modelId": "cstr/pyannote-v3-segmentation-GGUF",
"sha": "2a418bfa75a2ce8703c68248e865be96e24315b8",
"createdAt": "2026-04-12T14:06:43.000Z",
"lastModified": "2026-04-12T14:07:28.000Z",
"author": "cstr",
"downloads": 88,
"likes": 0,
"gated": false,
"private": false,
"pipeline_tag": "voice-activity-detection",
"library_name": "ggml",
"siblings_count": 3
}