Saltar al contenido
ModelPublicadoExterno
Descargar

BS RoFormer ONNX

Band-Split RoPE Transformer (BS-RoFormer) 的 ONNX 格式模型,用于音乐源分离(人声/伴奏分离)。

Fuentehuggingface.co/xycld/BS-RoFormer-ONNX/tree/f020228f4d25616c8ff4146c339c33687c0be43f
TipoOtherModelo baselucidrains/BS-RoFormerVersiónRevision f020228Ccalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
4,65–158 MB
Modelo base
lucidrains/BS-RoFormer
Versión
vRevision f020228
Actualizado
10 oct 2026
Descargas
0
Fuente
Hugging Face

Descripción de la fuente

BS-RoFormer ONNX (Vocals/Instrumental Separation)

Band-Split RoPE Transformer (BS-RoFormer) 的 ONNX 格式模型,用于音乐源分离(人声/伴奏分离)。

本仓库提供从 PyTorch checkpoint 转换的 ONNX 模型及其 uint8 动态量化版本。

Model Details

  • Architecture: BS-RoFormer (Band-Split RoPE Transformer)
  • Original Paper: Music Source Separation with Band-Split RoPE Transformer
  • Parameters: 159.8M (no-STFT variant)
  • Original Checkpoint: model_bs_roformer_ep_317_sdr_12.9755.ckpt (by viperx)
  • SDR Performance (MUSDB18HQ):
    • Vocals: 12.9 dB
    • Instrumental: 17.0 dB
FileFormatSizeDescription
bs_roformer_ep317_sdr12.9755.onnx + .dataONNX fp32~615 MBFull precision, external data
bs_roformer_ep317_sdr12.9755_quantized_uint8.onnxONNX uint8~158 MBDynamic quantized, single file

Usage

模型为 no-STFT 变体,需要先用 BS_roformer_processor 做 STFT 预处理,再将结果送入 ONNX 模型。

Quick Start

import onnxruntime as ort
import torch
import numpy as np
import soundfile as sf

# 1. Load ONNX model (quantized version, single file)
session = ort.InferenceSession(
    "bs_roformer_ep317_sdr12.9755_quantized_uint8.onnx",
    providers=['CPUExecutionProvider']
)

# 2. For the fp32 version with external data, load via onnx first:
# import onnx
# model = onnx.load("bs_roformer_ep317_sdr12.9755.onnx", load_external_data=True)
# session = ort.InferenceSession(model.SerializeToString(), providers=['CPUExecutionProvider'])

print("Model loaded!")
print(f"Input: {session.get_inputs()[0].name}, shape: {session.get_inputs()[0].shape}")
print(f"Output: {session.get_outputs()[0].name}, shape: {session.get_outputs()[0].shape}")

Full Inference Pipeline

完整的推理流程需要配合 ZFTurbo/MSS_ONNX_TensorRT 的 inference.py 使用:

git clone https://github.com/ZFTurbo/MSS_ONNX_TensorRT
cd MSS_ONNX_TensorRT

python inference.py \
    --model_type bs_roformer \
    --config_path path/to/model_bs_roformer_ep_317_sdr_12.9755.yaml \
    --input_folder path/to/input \
    --store_dir path/to/output \
    --use_onnx \
    --onnx_model_path path/to/bs_roformer_ep317_sdr12.9755.onnx

配置文件可从此处获取: model_bs_roformer_ep_317_sdr_12.9755.yaml

Attribution

Citation

@inproceedings{wang2024bsroformer,
  title={Music Source Separation with Band-Split RoPE Transformer},
  author={Wang, Ju-Chiang and Hsu, Wei-Tsung and Lai, Yi-Hsuan and others},
  booktitle={ICASSP 2024 - IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2024}
}

License

MIT License — 代码和转换工具均为 MIT 许可。模型权重由社区训练并公开分发,训练数据包含 MUSDB18HQ(研究用途)。建议商用前进一步确认训练数据的许可条款。

Fuentes

1 fuente
Hugging FacePrincipalVersión f020228f4d25616c8ff4146c339c33687c0be43f
huggingface.co/xycld/BS-RoFormer-ONNX/tree/f020228f4d25616c8ff4146c339c33687c0be43f

Verificado 22 ago

Artefactos del modelo

2 artefactos

bs_roformer_ep317_sdr12.9755_quantized_uint8.onnx

onnx · 158 MB · SHA-256 b86b6224ff34…07e9 · Hugging Face

Descargar

bs_roformer_ep317_sdr12.9755.onnx

onnx · 4,65 MB · SHA-256 357837834747…fe73 · Hugging Face

Descargar

Extractos de fuentes

2 extractos
Readme22 agohuggingface.co/xycld/BS-RoFormer-ONNX

--- library_name: onnxruntime license: mit datasets: - sidwswu/musdb18-hq pipeline_tag: audio-to-audio tags: - music - music-source-separation - audio - onnx - bs-roformer - roformer - vocals - instrumental - quantized base_model: lucidrains/BS-RoFormer --- # BS-RoFormer ONNX (Vocals/Instrumental Separation) Band-Split RoPE Transformer (BS-RoFormer) 的 ONNX 格式模型，用于音乐源分离（人声/伴奏分离）。 本仓库提供从 PyTorch checkpoint 转换的 ONNX 模型及其 uint8 动态量化版本。 ## Model Details - **Architecture**: BS-RoFormer (Band-Split RoPE Transformer) - **Original Paper**: [Music Source Separation with Band-Split RoPE Transformer](https://arxiv.org/abs/2309.02612) - **Parameters**: 159.8M (no-STFT variant) - **Original Checkpoint**: `model_bs_roformer_ep_317_sdr_12.9755.ckpt` (by viperx) - **SDR Performance** (MUSDB18HQ): - Vocals: **12.9 dB** - Instrumental: **17.0 dB** | File | Format | Size | Description | |------|--------|------|-------------| | `bs_roformer_ep317_sdr12.9755.onnx` + `.data` | ONNX fp32 | ~615 MB | Full precision, external data | | `bs_roformer_ep317_sdr12.9755_quantized_uint8.onnx` | ONNX uint8 | ~158 MB | Dynamic quantized, single file | ## Usage 模型为 **no-STFT 变体**，需要先用 `BS_roformer_processor` 做 STFT 预处理，再将结果送入 ONNX 模型。 ### Quick Start ```python import onnxruntime as ort import torch import numpy as np import soundfile as sf # 1. Load ONNX model (quantized version, single file) session = ort.InferenceSession( "bs_roformer_ep317_sdr12.9755_quantized_uint8.onnx", providers=['CPUExecutionProvider'] ) # 2. For the fp32 version with external data, load via onnx first: # import onnx # model = onnx.load("bs_roformer_ep317_sdr12.9755.onnx", load_external_data=True) # session = ort.InferenceSession(model.SerializeToString(), providers=['CPUExecutionProvider']) print("Model loaded!") print(f"Input: {session.get_inputs()[0].name}, shape: {session.get_inputs()[0].shape}") print(f"Output: {session.get_outputs()[0].name}, shape: {session.get_outputs()[0].shape}") ``` ### Full Inference Pipeline 完整的推理流程需要配合 [ZFTurbo/MSS_ONNX_TensorRT](https://github.com/ZFTurbo/MSS_ONNX_TensorRT) 的 `inference.py` 使用： ```bash git clone https://github.com/ZFTurbo/MSS_ONNX_TensorRT cd MSS_ONNX_TensorRT python inference.py \ --model_type bs_roformer \ --config_path path/to/model_bs_roformer_ep_317_sdr_12.9755.yaml \ --input_folder path/to/input \ --store_dir path/to/output \ --use_onnx...

Note22 agohuggingface.co/xycld/BS-RoFormer-ONNX

Source context: 0 downloads · 4 likes · Pipeline audio-to-audio · Library onnxruntime · Repo xycld/BS-RoFormer-ONNX