seaniezhao/torch_npss
Fork: 37 Star: 154 (更新于 2024-12-11 20:32:00)
license: MIT
Language: Jupyter Notebook .
pytorch implementation of Neural Parametric Singing Synthesizer 歌声合成
最后发布版本： v0.2.0 ( 2019-07-03 18:56:32)
torch_npss
implementation of A Neural Parametric Singing Synthesizer: https://arxiv.org/abs/1704.03809
- pretrained models are provided in snapshots/
- generated samples are in data/gen_wav/
dataset：https://drive.google.com/file/d/137dTlTiN7jSadV76sRDRwNJ_ysTz1psA/view?usp=sharing
try it out!
note: test labels are in data/timbre_model/test
pip install -r requirements.txt
python inference.py
try with your own data
put your own raw and label data in data/raw/
change custom_test in data/preprocess.py to True
run data/preprocess.py
run generate_test('your_file_name') in inference.py
train your own model
- put your audio and label in data/raw
- run data/preprocess.py
- adjust condition_channel in hparam.py according to your data
- run train_harmonoc.py train_aperoidic.py train_vuv.py
- if you have any questions feel free to leave an issue
A complete version of implementation which including F0 model and vuv model see here: https://github.com/seaniezhao/cnnpss
最近版本更新:(数据更新于 2024-10-09 20:14:09)
2019-07-03 18:56:32 v0.2.0
2019-05-11 10:44:28 v0.1.0
2019-05-05 11:00:38 v0.0.3
2019-04-12 00:36:57 v0.0.2
2019-03-27 19:09:47 v0.0.1
主题(topics):
sing, synthesizer
seaniezhao/torch_npss同语言 Jupyter Notebook最近更新仓库
2024-11-29 18:33:27 neo4j-labs/llm-graph-builder
2024-11-15 05:39:53 KindXiaoming/pykan
2024-11-11 10:53:33 microsoft/autogen
2024-10-09 04:20:42 Arize-ai/phoenix
2024-10-03 01:07:52 langchain-ai/langchain
2024-10-02 03:17:33 udlbook/udlbook