Alkd/campplus-zh-cn-common-200k-onnx
By Alkd · ↓ 0 · ♥ 0 · Updated 2026-03-07
What's in this repo
This page lists the files in Alkd/campplus-zh-cn-common-200k-onnx, including campplus_zh_cn_common_200k.onnx.
- 1 ONNX models (.onnx files)
- 3 files, including 1 .md, 1 .onnx
- Last updated 2026-03-07
ONNX files
| File | Size | Download |
|---|---|---|
| campplus_zh_cn_common_200k.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
CAMPPlus zh-cn-common-200k (ONNX)
Speaker embedding model for diarization, exported from ModelScope damo/speech_campplus_sv_zh-cn_16k-common.
Specs
- Architecture: CAM++ (Context-Aware Masking)
- Training data: CN-Celeb + CN Common (~200k speakers)
- Embedding dim: 192
- Input:
feats—[batch, 80, time](80-dim FBANK, 16 kHz, 10ms hop) - Output:
embs—[batch, 192]
Compatible with
pyannote-rs EmbeddingExtractor
(same feats/embs tensor names as wespeaker_en_voxceleb_CAM++.onnx).
Model info
Created: 2026-03-07
Updated: 2026-03-07
View on Hugging FaceFiles (3)
Related models
More from Alkd
More models
No task type declared.