Modelpublic

Acapellas/BSRoformer-GGUF

sourceHugging Faceupdated 8d agoView on Hugging Face

0likes56downloads

Model Card

BSRoformer-GGUF

Official GGUF model repository for the BSRoformer.cpp project. This repository contains BS Roformer/Mel-Band-Roformer models converted to the GGUF format, enabling high-performance, cross-platform local inference using the MelBandRoformer.cpp inference engine.

📦 Model List

This repository contains GGUF quantized versions of the following original models: | Original Model | Original Author | Recommended (Q80) | All Versions | | :--- | :--- | :--- | :--- | | [mel-band-roformer-deux](https://huggingface.co/becruily/mel-band-roformer-deux) | [becruily](https://huggingface.co/becruily) | [Download](https://huggingface.co/chenmozhijin/BSRoformer-GGUF/resolve/main/becruily/mel-band-roformer-deux/becruilydeux-Q80.gguf?download=true) | [View Models](https://huggingface.co/chenmozhijin/BSRoformer-GGUF/tree/main/becruily/mel-band-roformer-deux) | | [BS-RoFormer](https://huggingface.co/anvuew/BS-RoFormer) | [anvuew](https://huggingface.co/anvuew) | [Download](https://huggingface.co/chenmozhijin/BSRoformer-GGUF/resolve/main/anvuew/BS-RoFormer/BSRoformer-anvuew-Q80.gguf?download=true) | View Models | | MelBandRoformers (vocfv6) | [GaboxR67](https://huggingface.co/GaboxR67) | [Download](https://huggingface.co/chenmozhijin/BSRoformer-GGUF/resolve/main/GaboxR67/MelBandRoformers/melbandroformers/vocals/vocfv6-Q8_0.gguf?download=true) | View Models |

Quantization Types

To meet different hardware requirements, various quantized versions are provided:

—q8_0 (Recommended): 8-bit quantization. Significantly reduces memory usage and bandwidth requirements while maintaining audio quality almost identical to FP32.
—fp16: 16-bit floating point. Suitable for scenarios requiring maximum precision.
—q4_0 / q4_1 / q5_0 / q5_1: Lower-bit quantization, suitable for devices with low VRAM/RAM. (Note: Norm and Bias weights remain in FP32 to ensure numerical stability)

🚀 Usage

Please use with the BSRoformer.cpp command-line tool.

1. Download Tool

Download the executable for your system from BSRoformer.cpp (or compile it yourself).

2. Download Model

Download the desired .gguf file (e.g., voc_fv6-Q8_0.gguf) using the direct links in the Model List above, or browse all models from the Files and versions page of this repository.

3. Run Inference

bash

# Basic usage
./bs_roformer-cli model_q8_0.gguf input.wav output.wav
# Advanced usage (adjust chunk size and overlap to optimize quality)
./bs_roformer-cli model_q8_0.gguf input.wav output.wav --overlap 2