| Name | Date | Size | #Lines | LOC | ||
|---|---|---|---|---|---|---|
| .. | - | - | ||||
| data/ | 04-Jul-2025 | - | 229 | 155 | ||
| engine/ | 04-Jul-2025 | - | 141 | 80 | ||
| models/ | 04-Jul-2025 | - | 750 | 513 | ||
| scripts/ | 04-Jul-2025 | - | 504 | 332 | ||
| utils/ | 04-Jul-2025 | - | 1,715 | 1,284 | ||
| README.md | D | 04-Jul-2025 | 782 | 28 | 16 | |
| add_dataset_config.py | D | 04-Jul-2025 | 2.6 KiB | 78 | 56 | |
| make_default_setup.py | D | 04-Jul-2025 | 2 KiB | 57 | 42 | |
| make_test_config.py | D | 04-Jul-2025 | 3.3 KiB | 79 | 64 | |
| print_lpcnet_complexity.py | D | 04-Jul-2025 | 2.3 KiB | 65 | 49 | |
| test_lpcnet.py | D | 04-Jul-2025 | 2.8 KiB | 90 | 65 | |
| train_lpcnet.py | D | 04-Jul-2025 | 9.1 KiB | 273 | 195 |
README.md
1# LPCNet 2 3Incomplete pytorch implementation of LPCNet 4 5## Data preparation 6For data preparation use dump_data in github.com/xiph/LPCNet. To turn this into 7a training dataset, copy data and feature file to a folder and run 8 9python add_dataset_config.py my_dataset_folder 10 11 12## Training 13To train a model, create and adjust a setup file, e.g. with 14 15python make_default_setup.py my_setup.yml --path2dataset my_dataset_folder 16 17Then simply run 18 19python train_lpcnet.py my_setup.yml my_output 20 21## Inference 22Create feature file with dump_data from github.com/xiph/LPCNet. Then run e.g. 23 24python test_lpcnet.py features.f32 my_output/checkpoints/checkpoint_ep_10.pth out.wav 25 26Inference runs on CPU and takes usually between 3 and 20 seconds per generated second of audio, 27depending on the CPU. 28