Downloads · 30 days
0
ali-speaker-embedding-model
jellecali8/ali-speaker-embedding-model
ali-speaker-embedding-model is a feature extraction model from jellecali8. Use it when you need embeddings to search or compare text. It is set up for speechbrain. The card lists the license as mit.
Access
Public
Updated May 29, 2025
Repo size
2 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2 KB · 47%
At a glance
- Task
- Feature Extraction
- Library
- speechbrain
- License
- mit
- Access
- Public
- Created
- May 29, 2025
- Updated
- May 29, 2025
- SHA
- 8fa3e7fb
Base models
Model card
From the Hugging Face model README
Create README.md file first
readme_content = """
Ali Speaker Embedding (Model Repo)
This repository contains a trained speaker embedding vector for the Somali male speaker Ali, extracted using the speechbrain/spkrec-ecapa-voxceleb model.
Model details
- Format: PyTorch .pt
- File: Ali_speaker_embedding.pt
- Embedding size: 192-dimensional
- Language: Somali
- Gender: Male
- Audio source: 300+ clips from Ali
Usage
import torch
embedding = torch.load("Ali_speaker_embedding.pt")
- Task
- Feature Extraction
- Library
- speechbrain
- License
- mit
- Languages
- so
- Created
- May 29, 2025
- Updated
- May 29, 2025