2021-07-16 21:23:33 +08:00
2021-07-16 20:02:57 +08:00
2021-07-16 19:11:03 +08:00
2021-07-16 21:23:33 +08:00
2021-07-16 19:49:31 +08:00
2021-07-16 20:02:57 +08:00
2021-07-16 15:16:56 +08:00
2021-07-16 18:38:42 +08:00
2021-07-16 17:35:23 +08:00
2021-07-16 15:16:56 +08:00
2021-07-16 19:50:40 +08:00
2021-07-16 15:16:56 +08:00
2021-07-16 15:16:56 +08:00
2021-07-16 21:23:33 +08:00
2021-07-16 18:38:42 +08:00
2021-07-16 18:38:42 +08:00

kaldifeat

Wrap kaldi's feature computations to Python with PyTorch support.

Installation

From PyPi with pip

If you install kaldifeat using pip, it will also install PyTorch 1.8.1. If this is not what you want, please install kaldifeat from source (see below).

pip install kaldifeat

From source

The following are the commands to compile kaldifeat from source. We assume that you have installed cmake and PyTorch. cmake 3.11 is known to work. Other cmake versions may also work. PyTorch 1.8.1 is known to work. Other PyTorch versions may also work.

mkdir /some/path
git clone https://github.com/csukuangfj/kaldifeat.git
cd kaldifeat
python setup.py install

To test whether kaldifeat was installed successfully, you can run:

python3 -c "import kaldifeat; print(kaldifeat.__version__)"

Usage

Please refer to https://kaldifeat.readthedocs.io/en/latest/usage.html for how to use kaldifeat.

Description
Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - Provide C++ & Python API
Readme Apache-2.0 11 MiB
Languages
C++ 78%
Python 11.2%
CMake 6.7%
Shell 4.1%