cstr/cosyvoice3-0.5b-2512-GGUF
text-to-speech model by cstr
Older snapshot: check the original source for current information.
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.
GGUF conversion of FunAudioLLM/Fun-CosyVoice3-0.5B-2512 for use with CrispASR (--backend cosyvoice3-tts). CosyVoice3 is a streaming, multilingual, zero-shot voice-cloning TTS system from Alibaba's FunAudioLLM team. The 0.5B-2512 release is Apache-2.0 licensed and supports 9 languages plus 18 Chinese dialects. Output is 24 kHz mono. The model is a three-stage pipeline: Upstream ships two talker checkpoints in one repo: llm.pt (pre-trained) and llm.rl.pt (the same architecture after reinforcement learning, tuned by the authors for speech quality, pronunciation accuracy and generation stability). Only the talker differs — flow, HiFT, CAMPPlus, the speech tokenizer and the voice bank are shared, so switching is just pointing -m at the other LLM GGUF and leaving every companion file in place: CrispASR also ships --backend cosyvoice3-tts-rl (aliases cosyvoice3-rl, cv3-rl): the same engine, wired so that -m auto fetches the RL talker and reuses the shared companions. Both talkers are published here; keep whichever you prefer and delete the…
Read the full model card ↗ · Preview checked 2026-10-31T23:18:28.282Z
Inside the original model card — Document outline
- Fun-CosyVoice3-0.5B-2512 — GGUF
- Files
- Base vs RL talker
- Quant validation (ASR roundtrip on smoke prompt)
- Usage
- CrispASR (recommended)
- Voices
- Arbitrary-WAV cloning (native, no Python pre-bake)
- Tensor naming
- License
- Related links
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
cstr/cosyvoice3-0.5b-2512-GGUF is a text-to-speech model repository published by cstr on Hugging Face. A library was not reported.
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
- Not reported
- Recent downloads (30 days)
- 12,959
- Cumulative likes
- 15
- Hugging Face trending score
- 1
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-05-28T09:44:14.000Z
- Last modified
- 2026-08-05T17:46:04.000Z
Compatibility and lineage
Reported languages: zh, en, ja, ko, yue, fr, de, es, pt, it, ru
Reported base models: FunAudioLLM/Fun-CosyVoice3-0.5B-2512
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 2026-10-21T06:46:13.433Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.