BSRoformer GGUF

提供商chenmozhijin
分类audio-to-audio
许可证Apache-2.0
下载量9.3K
星标0

简介

BSRoformer GGUF 是一款专注于语音增强和噪声消除的音频模型。它通过 GGUF 格式化，极大降低了运行门槛，使得开发者和爱好者无需昂贵的 GPU 也能在本地设备上高效运行。该模型擅长将嘈杂环境中的人声精准提取，有效去除背景噪音，非常适合用于播客后期处理、会议记录预处理或实时语音通话优化。对于习惯使用 llama.cpp 等量化工具的用户来说，它提供了极佳的兼容性和部署便捷度，是目前轻量化语音增强的优秀选择。

核心亮点

  • 高效去除背景噪声，显著提升人声清晰度
  • GGUF 量化格式，低功耗且支持本地 CPU 运行
  • 适用于播客、会议记录等音频预处理场景
  • Apache-2.0 协议，对商业集成非常友好

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("chenmozhijin/BSRoformer-GGUF")
tokenizer = AutoTokenizer.from_pretrained("chenmozhijin/BSRoformer-GGUF")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download chenmozhijin/BSRoformer-GGUF

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download chenmozhijin/BSRoformer-GGUF config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('chenmozhijin/BSRoformer-GGUF')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/chenmozhijin/BSRoformer-GGUF

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/chenmozhijin/BSRoformer-GGUF

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('chenmozhijin/BSRoformer-GGUF')
tokenizer = AutoTokenizer.from_pretrained('chenmozhijin/BSRoformer-GGUF')

完整文档

来源: HuggingFace

---
tags:

  • audio

  • music

  • source-separation

  • mel-band-roformer

pipeline_tag: audio-to-audio
---

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 (Q8_0) | All Versions |
| :--- | :--- | :--- | :--- |
| mel-band-roformer-deux | becruily | Download | View Models |
| BS-RoFormer | anvuew | Download | View Models |
| MelBandRoformers (voc_fv6) | GaboxR67 | Download | 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

查看官方来源