RADTTS library
Project description
RADTTS library
This RADTTS library was changed to be used with vait library.
Original code, README.md and additional information:
https://github.com/NVIDIA/radtts
Instalation
1) Install RADTTS library
pip install radtts==22.12.28
2) Install CUDA 11.3 or 11.6
pip install -r requirements-cuda-11.3.txt
# or
pip install -r requirements-cuda-11.6.txt
3) Install maracas
git clone https://github.com/jfsantos/maracas /home/${USER}/maracas
cd /home/${USER}/maracas
pip install .
cd -
Usage: Training
radtts-train -c config_ljs_radtts.json -p train_config.output_directory=outdir
radtts-train -c config_ljs_radtts.json -p train_config.output_directory=outdir_dir train_config.warmstart_checkpoint_path=model_path.pt model_config.include_modules="decatndur"
Usage: Inferencing
radtts-inference -c CONFIG_PATH -r RADTTS_PATH -v HG_PATH -k HG_CONFIG_PATH -t TEXT_PATH -s ljs --speaker_attributes ljs --speaker_text ljs -o results/
radtts-inference_voice_conversion --radtts_path RADTTS_PATH --radtts_config_path RADTTS_CONFIG_PATH --vocoder_path HG_PATH --vocoder_config_path HG_CONFIG_PATH --f0_mean=211.413 --f0_std=46.6595 --energy_mean=0.724884 --energy_std=0.0564605 --output_dir=results/ -p data_config.validation_files="{'Dummy': {'basedir': 'data/', 'audiodir':'22khz', 'filelist': 'vc_audiopath_txt_speaker_emotion_duration_filelist.txt'}}"
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
radtts-22.12.29.tar.gz
(966.3 kB
view details)
Built Distribution
radtts-22.12.29-py3-none-any.whl
(991.7 kB
view details)
File details
Details for the file radtts-22.12.29.tar.gz
.
File metadata
- Download URL: radtts-22.12.29.tar.gz
- Upload date:
- Size: 966.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.3.1 CPython/3.10.9 Linux/6.0.0-6-amd64
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d828ed93cff8ef9f3ab149384e6e5e0da3dd414d83f29a40381c81350a244350 |
|
MD5 | 378b6ed456aab07cb67590e94f88aae0 |
|
BLAKE2b-256 | 865ad96eddf9d3ba353ce72cfc412b0800425da8b84eea3490bc9bf586055245 |
File details
Details for the file radtts-22.12.29-py3-none-any.whl
.
File metadata
- Download URL: radtts-22.12.29-py3-none-any.whl
- Upload date:
- Size: 991.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.3.1 CPython/3.10.9 Linux/6.0.0-6-amd64
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 959dc6e5d4cb4ee9be4dbebc368785a7837fd08bcde4f3c0d340bec4611d5199 |
|
MD5 | e4062dc7194a22508f3491476fe40237 |
|
BLAKE2b-256 | 0162cf7e9d05f2808f20d9032452b2b459fc81756b3fdb044ea45f369c0707fa |