Richopera/phrolova-rvc-v2
audio-to-audio 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 RVC v2 model converts singing or speech into the voice of Phrolova (弗洛洛) from Wuthering Waves, as voiced in Chinese by 张琦. This is voice conversion, not text-to-speech. My GPT-SoVITS model takes text and generates speech. This model takes an existing vocal recording and changes its timbre. A typical use is a song cover: feed it an isolated vocal track to hear the same performance in Phrolova’s voice. Start by comparing 200e and 150e on the same input. The final checkpoint is not necessarily the best for every song. If neither sounds right, try 100e or 120e. Keep the same index when switching checkpoints. Start with Pitch at 0 semitones. Compare short clips from a verse and a chorus. If the low notes sound muffled or creaky, try shifting up 1–2 semitones; if the high notes sound strained or buzzy, try shifting down 1–2. Choose by ear rather…
Read the full model card ↗ · Preview checked 2026-11-20T09:36:15.957Z
Inside the original model card — Document outline
- Phrolova (弗洛洛), Chinese Voice — RVC v2 (Applio)
- Model details
- Files and checkpoint selection
- Inference with Applio
- Recommended settings and pitch guide
- Pitch settings tested by ear
- Audio examples
- With accompaniment
- Isolated vocals
- Training data and run
- Known limitations
- Changelog
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: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
Richopera/phrolova-rvc-v2 is a audio-to-audio 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
- audio-to-audio
- 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
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-11-20T06:46:32.000Z
- Last modified
- 2026-11-20T06:48:13.000Z
Compatibility and lineage
Reported languages: zh
Reported base models: IAHispano/Applio
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.
Related models
nvidia/NVIDIA-NemotronLabs-RE-USE
inclusionAI/Ming-3.0-audio-flash