Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
|
|
1 year ago | |
|---|---|---|
| README.md | 1 year ago | |
0.1.在创建任务时选择reflow-vae-svc的镜像
192.168.204.22:5000/default-workspace/99280a9940ae44ca8f5892134386fddb/image:reflow-vae-svc
0.2.把程序转移到左侧文件区对应的目录
su
mv /root/* /tmp/code
0.3.把挂载好的数据集解压并移动到项目目录
mkdir /tmp/code/dataset_raw/
cp /tmp/dataset/* /tmp/code/dataset_raw/
cd /tmp/code/dataset_raw/
unzip ./*.zip
tar -xvf ./*.tar.gz
rm ./*.zip
rm ./*.tar.gz
find /tmp/code/dataset_raw -type f -iname "*.wav" -exec mv --backup=numbered -t /tmp/code/reflow-vae-svc/data/train/audio {} +
cd /tmp/code/reflow-vae-svc/
python draw.py
1.1.在预处理之前按需修改configs/reflow-vae-wavenet.yaml
1.2.预处理
python preprocess.py -c configs/reflow-vae-wavenet.yaml
1.3.训练(无底模)
python train.py -c configs/reflow-vae-wavenet.yaml
2.1.非实时推理
# 普通模式, 需要语义编码器, 比如 contentvec
python main.py -i <input.wav> -m <model_ckpt.pt> -o <output.wav> -k <keychange (semitones)> -tid <target_speaker_id> -step <infer_step> -method <method>
# VAE 模式, 无需语义编码器, 特化 sid 到 tid 的变声(或者音高编辑,如果sid == tid)
python main.py -i <input.wav> -m <model_ckpt.pt> -o <output.wav> -k <keychange (semitones)> -sid <source_speaker_id> -tid <target_speaker_id> -step <infer_step> -method <method>
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》