---
license: mit
language: so
tags:
  - tts
  - speaker-embedding
  - somali
  - speechbrain
  - vits
  - speecht5
library_name: speechbrain
base_model: speechbrain/spkrec-ecapa-voxceleb
pipeline_tag: feature-extraction
---

# Ali Speaker Embedding Dataset

This dataset contains a PyTorch `.pt` file that represents a speaker embedding for the Somali male speaker **Ali**.

The embedding was generated using the [`speechbrain/spkrec-ecapa-voxceleb`](https://huggingface.co/speechbrain/spkrec-ecapa-voxceleb) speaker recognition model from over 300 audio clips of the speaker's voice.

## Dataset Details

- **File**: `Ali_speaker_embedding.pt`
- **Format**: PyTorch tensor (`.pt`)
- **Embedding Size**: 192-dimensional
- **Language**: Somali (`so`)
- **Gender**: Male
- **Audio Source**: 300 high-quality `.wav` files from speaker Ali
- **Sample Rate**: 16kHz

## Usage Example

```python
import torch

# Load the embedding
embedding = torch.load("Ali_speaker_embedding.pt")