search

cvlab-kaist / GaussianTalker

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn and Seungryong Kim
Other
300 stars 36 forks source link

how to get <custom_aud>.npy? #21

Open liuzhougithub opened 5 months ago

liuzhougithub commented 5 months ago

I have a new_for_inference.wav file for inference,but I am not sure how to get the .npy file. HELP!!!

ankit-gahlawat-007 commented 5 months ago

You can run this command:

python data_utils/deepspeech_features/extract_ds_features.py --input new_for_inference.wav

liuzhougithub commented 5 months ago

You can run this command:

python data_utils/deepspeech_features/extract_ds_features.py --input new_for_inference.wav

It works! really really really thank you!

By the way, I think the project is not a true real-time talk face, I can't stream input wav data and get streaming output at the same time...

lokvke commented 5 months ago

You can run this command: python data_utils/deepspeech_features/extract_ds_features.py --input new_for_inference.wav

It works! really really really thank you!

By the way, I think the project is not a true real-time talk face, I can't stream input wav data and get streaming output at the same time...

你训练自己的模型了吗，效果怎么样

fransonwu commented 3 months ago

answered my question :)