OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Bsroformer.cpp

Bsroformer.cpp is a GGML-based C++ inference engine for BS Roformer and Mel-Band-Roformer audio source-separation models. It processes music to extract vocals or accompaniment, through a command-line WAV workflow or a C++ interface for application integration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Bsroformer.cpp — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to run BS Roformer or Mel-Band-Roformer separation locally through a CLI or C++ integration, and can provide a compatible GGUF model and 44.1 kHz audio.

Who it is for

  • People who need to extract vocals or accompaniment from 44.1 kHz WAV music.
  • Developers embedding source-separation inference in a C++ audio or music application.
  • Users building an audio-processing workflow that can use GGUF models and GGML.

Documented uses

  • Separate a music track into vocal or accompaniment output.
  • Process WAV files through the command-line tool with adjustable chunking and overlap.
  • Integrate model inference, audio I/O, progress reporting and cancellation into a C++ application.
Before you choose

Requirements & limits

The project is publicly available on GitHub and identifies its license as MIT. Its README describes pre-built binaries and GGUF models.

  • The CLI input requirement is 44.1 kHz WAV; mono and stereo are supported.
  • The supported model architectures are BS Roformer and Mel-Band-Roformer, using GGUF model files.
  • CPU, CUDA and Vulkan backend availability depends on the GGML build configuration.
  • Chunk size trades memory use against processing efficiency; additional overlap may reduce reassembly artifacts but increases inference time.
  • Source builds require CMake 3.17+, a C++17-compatible compiler and GGML source.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build the CLI from source

Configure and compile the command-line tool with GGML.

Before you start

  • CMake 3.17 or later.
  • A C++17-compatible compiler: MSVC 2019+, GCC 9+, or Clang 10+.
  • GGML source code as a submodule or local directory.

Steps

  1. Provide GGML source, either as a submodule or local directory.

  2. Configure a CPU build with cmake -B build.

  3. Compile with cmake --build build --config Release --parallel.

Expected outcome

The documented build configuration compiles the project; the CLI build option is enabled by default.

Guide limitations

  • CUDA acceleration requires configuring the build with -DGGML_CUDA=ON.
  • This recipe covers compilation, not model acquisition or running inference.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Bsroformer.cppSeparate a music track into vocal or accompaniment output.CLI, Linux, macOS, WindowsThe project is publicly available on GitHub and identifies its license as MIT. Its README describes pre-built binaries and GGUF models.
BluettsGenerate speech audio from text in a supported language.CLI, Linux, macOS, WindowsThe repository is public and identifies the project license as MIT.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
chenmozhijin/BSRoformer.cpp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction