voice detect needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 0.0 GB to 1.3 GB.
Voice detection model for speaker recognition and voice analysis
The voice-detect GGUF models are designed for the LocalAI voice-detect backend. They are self‑contained, metadata‑driven models produced by voice-detect.cpp, a C++/ggml engine. Each model uses an 80‑dim FBank front end and a different speaker encoder graph.
Good at
- Speaker verification
- Voice analysis
- Low‑memory inference
Limits
- No vision support
- License varies by model
- Requires 8‑k context for memory estimates
Best for
- Embedded speaker ID
- Research voice analysis
- Local AI inference
Who it’s for. Developers building local voice‑recognition systems or researchers needing lightweight speaker embeddings. The models are suitable for non‑commercial or commercial use depending on the chosen encoder.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.0 GB | 0.5 GB | Fits | Get file → | |
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| — | 0.4 GB | 0.9 GB | Fits | Get file → | |
| — | 1.3 GB | 1.9 GB | Fits | Get file → |
For 8‑GB VRAM, the 0.03‑GB files use about 0.5‑GB memory at 8‑k context, suitable for low‑budget setups. The 0.38‑GB file uses 0.9‑GB memory, and the 1.27‑GB file uses 1.9‑GB memory, suitable for higher‑capacity GPUs.
What GPU do you need for voice detect?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (1.3 GB file, about 1.9 GB in use).
Which voice detect quant should you choose?
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about voice detect
How much VRAM does voice detect need?
About 0.5 GB at its main file with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run voice detect on an 8 GB GPU?
Yes, with the smaller files: the 1.3 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of voice detect GGUF?
It depends on the quant: file is 0.0 GB, file is 0.0 GB, file is 0.0 GB, file is 0.1 GB, file is 0.4 GB, file is 1.3 GB.
Where can I download voice detect GGUF?
The files are on Hugging Face in the mudler/voice-detect-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does voice detect use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run the 0.03‑GB model on 8 GB VRAM?
Yes, the 0.03‑GB model requires about 0.5‑GB memory at 8‑k context, well within 8‑GB VRAM.
What license applies to the speaker encoders?
The four speaker encoders are commercial‑friendly; the two wav2vec2 heads are CC‑BY‑NC‑SA‑4.0 and for research/non‑commercial use only.
Does the model support vision tasks?
No, the voice-detect models are purely audio and do not support vision.