Overview

The DenoisingAutoencoder is a specialized speech-enhancement model designed to isolate clean audio signals from noisy environments. Unlike general-purpose audio models, this architecture focuses specifically on noise reduction, making it ideal for preprocessing pipelines in voice-to-text (ASR) systems or improving audio quality for VoIP and communication apps. For developers, its Apache-2.0 license ensures flexible integration into both open-source and commercial projects. It functions as a signal-processing layer that maps corrupted audio inputs to a reconstructed, noise-free output, effectively increasing the signal-to-noise ratio (SNR) before the audio reaches downstream analysis models.

Highlights

Specialized in high-fidelity speech noise reduction
Optimizes audio quality for ASR preprocessing
Permissive Apache-2.0 license for commercial use
Efficiently isolates voice from background interference

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("Bmo411/DenoisingAutoencoder")
tokenizer = AutoTokenizer.from_pretrained("Bmo411/DenoisingAutoencoder")

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

huggingface-cli download Bmo411/DenoisingAutoencoder

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

huggingface-cli download Bmo411/DenoisingAutoencoder config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Bmo411/DenoisingAutoencoder')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/Bmo411/DenoisingAutoencoder

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Bmo411/DenoisingAutoencoder

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

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Bmo411/DenoisingAutoencoder')
tokenizer = AutoTokenizer.from_pretrained('Bmo411/DenoisingAutoencoder')