sepformer dns4 16k enhancement

Providerspeechbrain
Categoryspeech-enhancement
Licenseapache-2.0
Downloads563
Stars0

Overview

SepFormer DNS4 16k is a specialized speech enhancement model designed to isolate clean voice signals from noisy environments. Built on the SpeechBrain framework, it leverages the SepFormer architecture—a transformer-based approach that excels at capturing long-term dependencies in audio sequences compared to traditional RNNs. For developers, this model is ideal for preprocessing pipelines in VoIP, automated transcription (ASR), or hearing aid software where reducing ambient noise is critical for accuracy. It operates on 16kHz audio, making it compatible with most standard telephony and voice-command datasets. Integration is straightforward via the SpeechBrain library, allowing for efficient deployment in Python-based audio processing stacks.

Highlights

  • Transformer-based architecture for superior noise suppression
  • Optimized for 16kHz audio sampling rates
  • Seamless integration via the SpeechBrain framework
  • Apache-2.0 license for flexible commercial deployment
  • Ideal preprocessing for ASR and voice communication

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("speechbrain/sepformer-dns4-16k-enhancement")
tokenizer = AutoTokenizer.from_pretrained("speechbrain/sepformer-dns4-16k-enhancement")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download speechbrain/sepformer-dns4-16k-enhancement

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download speechbrain/sepformer-dns4-16k-enhancement config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('speechbrain/sepformer-dns4-16k-enhancement')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/speechbrain/sepformer-dns4-16k-enhancement

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/speechbrain/sepformer-dns4-16k-enhancement

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('speechbrain/sepformer-dns4-16k-enhancement')
tokenizer = AutoTokenizer.from_pretrained('speechbrain/sepformer-dns4-16k-enhancement')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model speechbrain/sepformer-dns4-16k-enhancement

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model speechbrain/sepformer-dns4-16k-enhancement README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('speechbrain/sepformer-dns4-16k-enhancement')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/speechbrain/sepformer-dns4-16k-enhancement.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/speechbrain/sepformer-dns4-16k-enhancement.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'speechbrain/sepformer-dns4-16k-enhancement')

Full Documentation

来源: HuggingFace

---
language:
- "en"
- "de"
- "ru"
- "fr"
- "it"
- "es"
thumbnail:
tags:

  • audio-to-audio

  • Speech Enhancement

  • DNS-4

  • SepFormer

  • Transformer

  • pytorch

  • speechbrain

  • Microsoft DNS Challenge

  • Deep Noise Suppression Challenge – ICASSP 2022

license: "apache-2.0"
datasets:
  • DNS-4

metrics:
  • SI-SNR

  • PESQ

  • SIG

  • BAK

  • OVRL

model-index:
  • name: sepformer-dns4-16k-enhancement

results:
- task:
name: Speech Enhancement
type: speech-enhancement
dataset:
name: DNS-4
type: deep-noise-suppression-challenge-icassp-2022
split: baseline-dev-set
args:
language: de
metrics:
- name: DNSMOS SIG
type: sig
value: '2.999'
- name: DNSMOS BAK
type: bak
value: '3.076'
- name: DNSMOS OVRL
type: ovrl
value: '2.437'
---

<iframe src="https://ghbtns.com/github-btn.html?user=speechbrain&repo=speechbrain&type=star&count=true&size=large&v=2" frameborder="0" scrolling="0" width="170" height="30" title="GitHub"></iframe>
<br/><br/>

SepFormer trained on Microsoft DNS-4 (Deep Noise Suppression Challenge 4 – ICASSP 2022) for speech enhancement (16k sampling frequency)

This repository provides all the necessary tools to perform speech enhancement (denoising) with a SepFormer model, implemented with SpeechBrain. The model is trained on 1300HRS of Microsoft-DNS 4 dataset with 16k sampling frequency. For a better experience we encourage you to learn more about SpeechBrain. Evaluation on DNS4 2022 baseline dev set using DNSMOS are-

| Release | SIG | BAK | OVRL |
|:-------------:|:--------------:|:--------------:|:--------------:|
| 08-01-23 | 2.999 | 3.076 | 2.437 |

DNSMOS - deep noise suppression (DNS)- mean opinion score (MOS) is a non-intrusive evaluation metric. It computes 3 scores– SIG (speech quality), BAK (background noise quality), and OVRL (overall quality) each on a scale of 1 to 5, with 5 being the best quality.

Install SpeechBrain

First of all, please install SpeechBrain with the following command:

code
pip install speechbrain

Please notice that we encourage you to read our tutorials and learn more about SpeechBrain.

Perform speech enhancement on your own audio file

python
from speechbrain.inference.separation import SepformerSeparation as separator
import torchaudio

model = separator.from_hparams(source="speechbrain/sepformer-dns4-16k-enhancement", savedir='pretrained_models/sepformer-dns4-16k-enhancement')


for custom file, change path

est_sources = model.separate_file(path='speechbrain/sepformer-dns4-16k-enhancement/example_dns4-16k.wav')

torchaudio.save("enhanced_dns4-16k.wav", est_sources[:, :, 0].detach().cpu(), 16000)

Inference on GPU

To perform inference on the GPU, add run_opts={"device":"cuda"} when calling the from_hparams method.

You can find our training results (models, logs, etc) here.

Limitations

The SpeechBrain team does not provide any warranty on the performance achieved by this model when used on other datasets.

Referencing SpeechBrain

bibtex
@misc{speechbrain,
  title={{SpeechBrain}: A General-Purpose Speech Toolkit},
  author={Mirco Ravanelli and Titouan Parcollet and Peter Plantinga and Aku Rouhe and Samuele Cornell and Loren Lugosch and Cem Subakan and Nauman Dawalatabad and Abdelwahab Heba and Jianyuan Zhong and Ju-Chieh Chou and Sung-Lin Yeh and Szu-Wei Fu and Chien-Feng Liao and Elena Rastorgueva and François Grondin and William Aris and Hwidong Na and Yan Gao and Renato De Mori and Yoshua Bengio},
  year={2021},
  eprint={2106.04624},
  archivePrefix={arXiv},
  primaryClass={eess.AS},
  note={arXiv:2106.04624}
}

Referencing SepFormer

bibtex
@inproceedings{subakan2021attention,
      title={Attention is All You Need in Speech Separation}, 
      author={Cem Subakan and Mirco Ravanelli and Samuele Cornell and Mirko Bronzi and Jianyuan Zhong},
      year={2021},
      booktitle={ICASSP 2021}
}

Referencing ICASSP 2022 Deep Noise Suppression Challenge

bibtex
@inproceedings{dubey2022icassp,
  title={ICASSP 2022 Deep Noise Suppression Challenge},
  author={Dubey, Harishchandra and Gopal, Vishak and Cutler, Ross and Matusevych, Sergiy and Braun, Sebastian and Eskimez, Emre Sefik and Thakker, Manthan and Yoshioka, Takuya and Gamper, Hannes and Aichner, Robert},
  booktitle={ICASSP},
  year={2022}
}

About SpeechBrain

  • Website: https://speechbrain.github.io/
  • Code: https://github.com/speechbrain/speechbrain/
  • HuggingFace: https://huggingface.co/speechbrain/
View official source
Join our Telegram