How to use your own audio files

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 use your own audio files #49

Open ShelikeSnow opened 2 months ago

ShelikeSnow commented 2 months ago

python render.py -s data --model_path /root/autodl-tmp/GaussianTalker/data --configs arguments/64_dim_1_transformer.py --iteration 10000 --batch 128 --custom_wav test.mp3 --skip_test This is my order, and the generated video is still the same. Non-test.MP3 content

jarun-title commented 2 months ago

run this command with your audio file to get preprocessed audio npy file and follow this guide in readme

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