speech enhancement mask resnet unet quantized
Overview
This model implements a quantized ResNet-U-Net architecture specifically designed for speech enhancement via masking. By leveraging a U-Net backbone with residual connections, it effectively separates target speech from background noise in the time-frequency domain. The quantization ensures a smaller memory footprint and faster inference, making it suitable for deployment on edge devices or real-time audio processing pipelines. Developers can integrate this into noise-reduction middleware or voice-command pre-processing stages where low-latency execution is critical. Compared to full-precision models, it maintains competitive denoising performance while significantly reducing computational overhead.
Highlights
- Quantized ResNet-U-Net architecture for efficient edge deployment
- Specialized in time-frequency masking for noise reduction
- Low-latency inference ideal for real-time audio pipelines
- Apache-2.0 license allows flexible commercial integration
Usage
Install
# Install Hugging Face transformers
pip install transformers torchSDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("huseinzol05/speech-enhancement-mask-resnet-unet-quantized")
tokenizer = AutoTokenizer.from_pretrained("huseinzol05/speech-enhancement-mask-resnet-unet-quantized")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_hubCLI Download
Download the full repository
Download the full repository
huggingface-cli download huseinzol05/speech-enhancement-mask-resnet-unet-quantizedDownload 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 huseinzol05/speech-enhancement-mask-resnet-unet-quantized config.json --local-dir ./dirSee 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('huseinzol05/speech-enhancement-mask-resnet-unet-quantized')Git Download
Make sure git-lfs is installed first
Git Download
git lfs install
git clone https://huggingface.co/huseinzol05/speech-enhancement-mask-resnet-unet-quantizedTo skip LFS large-file downloads, use:
Skip LFS
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/huseinzol05/speech-enhancement-mask-resnet-unet-quantizedModel 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 torchLoad the model and run inference
Load the model and run inference
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('huseinzol05/speech-enhancement-mask-resnet-unet-quantized')
tokenizer = AutoTokenizer.from_pretrained('huseinzol05/speech-enhancement-mask-resnet-unet-quantized')