breizhn/DTLN
Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.
This tool helps improve the clarity of spoken audio by removing background noise. It takes noisy speech recordings as input and produces clean, enhanced speech as output, making it easier to understand. This is ideal for anyone working with audio recordings that suffer from unwanted background sounds, such as researchers, podcasters, or customer service analysts.
698 stars. No commits in the last 6 months.
Use this if you need to clean up audio recordings in real-time or process large batches of noisy speech files to improve their intelligibility.
Not ideal if your primary goal is acoustic echo cancellation rather than general noise suppression, although a related tool for that specific purpose is mentioned.
Stars
698
Forks
172
Language
Python
License
MIT
Category
Last pushed
Jul 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/breizhn/DTLN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
iver56/audiomentations
A Python library for audio data augmentation. Useful for making audio ML models work well in the...
Rikorose/DeepFilterNet
Noise supression using deep filtering
torchsynth/torchsynth
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
marl/openl3
OpenL3: Open-source deep audio and image embeddings
archinetai/audio-data-pytorch
A collection of useful audio datasets and transforms for PyTorch.