Richopera/Phrolova-zh-gpt-sovits-v2proplus
AI model by Richopera
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.
简体中文 This text-to-speech model reproduces the voice of Phrolova (弗洛洛) from Wuthering Waves, as voiced in Chinese by 张琦. What I love about 张琦’s performance is how Phrolova changes the way she speaks from scene to scene. 张琦 brings several distinct “Phrolovas” to life, each brilliantly in character. The model was trained on Chinese speech and inherits GPT-SoVITS’s native cross-language synthesis capability. At inference time, provide a reference clip and its exact transcript. The model uses the clip to guide the timbre and delivery of the generated speech. For conversion of existing vocals rather than text-to-speech, see my Phrolova RVC model. Start with 弗洛洛pro/. The September 2026 pro release uses a larger, cleaner dataset than the June 2026 first generation. Both are included if you want to compare them by ear. Load both checkpoints from the same generation in a GPT-SoVITS environment that supports v2ProPlus checkpoints. Do not mix a…
Read the full model card ↗ · Preview checked 2026-11-20T09:38:07.758Z
Inside the original model card — Document outline
- Phrolova (弗洛洛), Chinese Voice — GPT-SoVITS v2ProPlus
- Two generations of checkpoints
- Training
- Inference
- Audio examples
- Usage terms
- Attribution when publishing
- Acknowledgments
- Contact
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. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Richopera/Phrolova-zh-gpt-sovits-v2proplus is a task-unspecified model repository published by Richopera 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
- Not reported
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- Not reported — check the model card
- Access
- Not gated by Hugging Face
- Created
- 2026-11-20T06:38:11.000Z
- Last modified
- 2026-11-20T06:38:11.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
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 2026-11-20T07:02:14.348Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.