davidxifeng/zipvoice-gguf
text-to-speech model by davidxifeng
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Ready-to-run GGUF packages of ZipVoice-Distill (k2-fsa), a zero-shot voice-cloning TTS with a TTSZipformer flow-matching backbone and a Vocos 24 kHz vocoder, packaged for the audio.cpp engine. Each file is fully self-contained: flow-matching model + bundled Vocos vocoder + embedded text-frontend sidecars (tokens.txt, model.json, zh tables, jieba dictionaries). Output: 24 kHz mono WAV. Q80 is the recommended download. Weights are stored as int8 blocks (one F16 scale per 32 weights); activations stay F32 and the kernels dequantize each block on the fly — no full-model dequantization at load, no int8 arithmetic. Quality is transparent to the ear; 8-step distilled sampling, guidance scale 3, time shift 0.5. Lower-bit variants (q6k … q40) are deliberately not provided — they trade audible quality…
Read the full model card ↗ · Preview checked 2026-09-30T06:41:15.314Z
Inside the original model card — Document outline
- ZipVoice-Distill GGUF for audio.cpp
- Files
- Q80 vs F32 (Apple M3, Metal, 34 s utterance)
- Usage
- Install with the audio.cpp model manager
- Direct synthesis (CLI)
- Provenance & conversion
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
davidxifeng/zipvoice-gguf is a text-to-speech model repository published by davidxifeng on Hugging Face. The source reports the ggml library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- ggml
- Recent downloads (30 days)
- 10,403
- Cumulative likes
- 1
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-18T03:08:46.000Z
- Last modified
- 2026-09-18T12:36:39.000Z
Compatibility and lineage
Reported languages: zh, en
Reported base models: k2-fsa/ZipVoice
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-30T06:39:16.936Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.