RVC-Project/Retrieval-based-Voice-Conversion-WebUI
48.5
Weak · 14 November 2026
32.3k
lines of production code
Python
primary language
7
measurements over time
What this system is
Features
Add CLI interface and GPU-accelerated audio processing for inference
A new command-line interface (CLI) is introduced for offline RVC inference, allowing users to process audio files or directories with options for speaker ID, pitch shift, F0 method, and output format. The \infer\ module is significantly expanded with new files for audio handling (\audio.py\), CLI logic (\cli.py\), and model components (\fcpe.py\, \hubert.py\, \module/...\). Audio loading and resampling now support GPU acceleration via \torchaudio\ when available, falling back to FFmpeg/CPU otherwise. Additionally, CUDA Graph support is added to accelerate FCPE and HuBERT inference, improving performance on compatible GPUs.
infer · high confidence
Add RVC Realtime VST2/VST3 plugin project
A new Windows x64 VST2 and VST3 plugin project has been added to the repository. The plugin implements real-time voice conversion using C++17 and iPlug2, with model loading and RVC inference handled by a separate Python worker process. The project includes build scripts, test scripts, and bilingual developer guides (English and Simplified Chinese) to help developers compile and use the plugin.
RVCRealtimeVST · high confidence
Add RVC Realtime and Offline WebUIs with GPU acceleration and DirectML support
The application now includes dedicated launch scripts and Python entry points for both a real-time voice conversion interface (realtime\_gui.py) and an offline WebUI (webui.py). The offline WebUI defaults to disabling CUDA Graphs for stability, while the real-time GUI supports GPU processing for audio loading, resampling, and inference to improve efficiency. The project also introduces a new dependency on the pymss library for vocal separation, with specific requirements files (requirments\_cu118\_py312.txt, requirments\_cu128\_py312.txt, requirments\_cpu\_py312.txt) that configure PyTorch, ONNX Runtime, and other libraries for CUDA 11.8, CUDA 12.8, and CPU/DirectML environments respectively.
(repo-wide) · high confidence
Added configuration files and CUDA Graph support
New configuration files have been added for model versions v1 and v2 at sampling rates of 32k, 40k, and 48k, defining training and model parameters. Additionally, the system now supports CUDA Graph inference acceleration, with the configuration module automatically detecting and enabling CUDA Graphs on compatible hardware to improve performance.
configs · high confidence
Adds i18n support for training workflows
Introduces a new internationalization system for the training interface, providing English, Spanish, French, and Italian translations for all UI strings related to model training, data preprocessing, and feature extraction.
i18n · high confidence
Introduce new vocal separation and bandit splitting modules
Added new modules for vocal separation and bandit-based audio splitting. The vocal remover now includes a comprehensive set of model metadata, a common separator base class, and a full MLX backend for MPS devices, alongside standard PyTorch implementations. Additionally, a new bandit module was introduced, featuring spectral components, band splitting logic, and a multi-source multi-mask RNN model for separating audio into different frequency bands.
(repo-wide) · high confidence
Introduce pymss-based music source separation and CUDA Graph acceleration
The tools directory now includes a new 'pymss' package that provides a Python API for music source separation, including model cataloging, downloading, audio I/O, and ensemble utilities. This replaces the previous UVR5 separation backend. Additionally, a new 'cuda\_graph.py' module adds CUDA Graph inference acceleration support, while 'process\_utils.py' adds robust process tree termination, 'file\_io.py' adds safe text file reading, and 'multispeaker.py' adds manifest building for multi-speaker training sets.
tools · high confidence
New multi-speaker training pipeline and data processing tools
Added a complete set of scripts and utilities for multi-speaker voice cloning training. This includes \train.py\ for the main training loop with distributed data parallel support, \data\_utils.py\ for loading and batching audio/text pairs, \preprocess.py\ for audio slicing and resampling, \extract\_f0.py\ and \extract\_hubert\_feature.py\ for pitch and HuBERT feature extraction, \train\_index.py\ for FAISS index training, and supporting modules for loss functions, mel processing, and checkpoint management.
train · high confidence
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
How this codebase got here
Score
- CAI 41 → 49 (+7.8)
- Rubric changed (rubric-2026.10.5 → rubric-2026.11.4) — scores are not directly comparable.
Lenses
- Code Health 69 → 69 (-0.1)
- Architecture 82 → 84 (+1.6)
- Maturity 66 → 68 (+1.3)
- Readiness 24 → 20 (-4.1)
- Security 35 → 82 (+46.9)
- Performance 100 → 100 (+0.0)
Resolved (68)
- Attention._cuda_or_default_attention (cognitive 18) (tools/pymss_core/modules/bs_roformer/transformer.py)
- Duplicated block (11 lines × 2) (tools/pymss_core/modules/demucs_local.py)
- Duplicated block (13 lines × 2) (tools/pymss_core/modules/bs_roformer/mlx_attention.py)
- Duplicated block (5 lines × 2) (tools/pymss_core/modules/bandit_mlx.py)
- Duplicated block (6 lines × 2) (tools/pymss_core/modules/bandit_mlx.py)
- Duplicated block (9 lines × 2) (tools/pymss/cli.py)
- Duplicated block (9 lines × 2) (train/data_utils.py)
- Duplicated block (9 lines × 3) (tools/pymss_core/modules/bandit_mlx.py)
- FileTooLong: bs_roformer/bands.py (tools/pymss_core/modules/bs_roformer/bands.py)
- FileTooLong: bs_roformer/mlx_roformer.py (tools/pymss_core/modules/bs_roformer/mlx_roformer.py)
- FileTooLong: modules/demucs_local.py (tools/pymss_core/modules/demucs_local.py)
- FileTooLong: modules/legacy_demucs.py (tools/pymss_core/modules/legacy_demucs.py)
- FileTooLong: pymss/separator.py (tools/pymss/separator.py)
- FileTooLong: pymss/utils.py (tools/pymss/utils.py)
- FileTooLong: pymss/workflow.py (tools/pymss/workflow.py)
- FileTooLong: server/app.py (tools/pymss/server/app.py)
- FileTooLong: tools/pymss_webui.py (tools/pymss_webui.py)
- HTDemucs.init (cognitive 43) (tools/pymss_core/modules/demucs4ht.py)
- HTDemucs.init (cyclomatic 25) (tools/pymss_core/modules/demucs4ht.py)
- HTDemucs.forward (cognitive 42) (tools/pymss_core/modules/demucs4ht.py)
- …and 48 more
New (78)
- Edited copies of one member (3 members, 11+ corresponding lines) (tools/pymss_core/modules/bs_roformer/mlx_roformer.py)
- Edited copies of one member (3 members, 14+ corresponding lines) (tools/pymss_core/modules/bandit_mlx.py)
- Edited copies of one member (3 members, 18+ corresponding lines) (tools/pymss_core/modules/bs_roformer/bands.py)
- Edited copies of one member (3 members, 22+ corresponding lines) (tools/pymss_core/modules/bandit_mlx.py)
- Edited copies of one member (3 members, 30+ corresponding lines) (webui.py)
- Edited copies of one member (3 members, 34+ corresponding lines) (tools/pymss_core/modules/bandit/core/model/bsrnn/core.py)
- Edited copies of one member (3 members, 7+ corresponding lines) (tools/pymss_core/modules/bandit/core/model/bsrnn/utils.py)
- Edited copies of one member (3 members, 7+ corresponding lines) (tools/pymss_core/modules/demucs4ht.py)
- Edited copies of one member (3 members, 9+ corresponding lines) (tools/pymss_core/modules/bs_roformer/bs_roformer.py)
- Edited copies of one member (4 members, 4+ corresponding lines) (tools/pymss_core/modules/bandit_mlx.py)
- Edited copies of one member (5 members, 14+ corresponding lines) (tools/pymss_core/modules/bs_roformer/mlx_roformer.py)
- Edited copies of one member (7 members, 3+ corresponding lines) (tools/pymss_core/modules/apollo_mlx.py)
- Edited copy of a member (10 corresponding lines) (tools/pymss/modules/vocal_remover/vr_mlx.py)
- Edited copy of a member (10 corresponding lines) (tools/pymss_core/modules/bs_roformer/common.py)
- Edited copy of a member (10 corresponding lines) (tools/pymss_core/modules/legacy_demucs.py)
- Edited copy of a member (12 corresponding lines) (tools/pymss_core/modules/bandit/maskestim.py)
- Edited copy of a member (13 corresponding lines) (infer/vc/modules.py)
- Edited copy of a member (13 corresponding lines) (tools/pymss_core/modules/_dsp.py)
- Edited copy of a member (13 corresponding lines) (tools/pymss_core/modules/bandit_mlx.py)
- Edited copy of a member (13 corresponding lines) (tools/pymss_core/modules/demucs_local.py)
- …and 58 more
Written by cca.canine.dev from the codebase's own history, inside the signed delivery this page is composed from.
Survey your own repository
RVC-Project/Retrieval-based-Voice-Conversion-WebUI was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point a surveyor at a repository you know and see whether you agree with it.
About this page
- The score is its most recent published measurement, taken on 14 November 2026 at a pinned commit. It is not a live figure and does not change until the project is measured again.
- Measured at commit 81eed5e8f68b6bed1789f682fe78cdd324495afc — the exact code this score is about.
- Scored under rubric-2026.11.4 — the same rubric and the same method as every other entry in this index.
- Measured by Canine Code Analyzer (cca.canine.dev) using cca measure-2026.11.65+preprod-36d4cd83012f.