Instructions to use niobures/DTLN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- TF-Keras
How to use niobures/DTLN with TF-Keras:
# Note: 'keras<3.x' or 'tf_keras' must be installed (legacy), and from_pretrained_keras was removed in huggingface_hub 1.0. # See https://github.com/keras-team/tf-keras for more details. # !pip install "huggingface_hub<1.0" tf_keras from huggingface_hub import from_pretrained_keras model = from_pretrained_keras("niobures/DTLN") - Notebooks
- Google Colab
- Kaggle
|
Download models/ailia-models/code/README.md from niobures/DTLN: direct link, hf CLI and curl.
- Browser
- Download file 988 Bytes
-
https://huggingface.co/niobures/DTLN/resolve/main/models/ailia-models/code/README.md
- Command line
-
hf download hf://niobures/DTLN/models/ailia-models/code/README.md
-
curl -L -o README.md https://huggingface.co/niobures/DTLN/resolve/main/models/ailia-models/code/README.md
988 Bytes
Dual-signal Transformation LSTM Network
input
audio file(16kHz)
LibriSpeech ASR corpus
http://www.openslr.org/12
1221-135766-0000.wav
Output
Audio file with noise removed
Usage
Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.
For the sample wav,
$ python3 dtln.py
If you want to specify the audio, put the file path after the --input option.
$ python3 dtln.py --input AUDIO_FILE
If you run by onnxruntime instead of ailia, you use --onnx option.
Reference
Framework
Pytorch
Model Format
ONNX opset=11