deepgeek/MuseTalk
2
0
Fork 0
mirror of https://github.com/TMElyralab/MuseTalk.git synced 2026-02-05 18:09:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: data preprocessing and training (#294)

Browse Source 
* docs: update readme

* docs: update readme

* feat: training codes

* feat: data preprocess

* docs: release training
This commit is contained in:
Zhizhou Zhong
2025-04-04 22:10:03 +08:00
committed by GitHub
parent e636166b85
commit 1ab53a626b
23 changed files with 3854 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
configs/training/syncnet.yaml Normal file
View File

@@ -0,0 +1,19 @@
# This file is modified from LatentSync (https://github.com/bytedance/LatentSync/blob/main/latentsync/configs/training/syncnet_16_pixel.yaml).
model:
audio_encoder: # input (1, 80, 52)
in_channels: 1
block_out_channels: [32, 64, 128, 256, 512, 1024, 2048]
downsample_factors: [[2, 1], 2, 2, 1, 2, 2, [2, 3]]
attn_blocks: [0, 0, 0, 0, 0, 0, 0]
dropout: 0.0
visual_encoder: # input (48, 128, 256)
in_channels: 48
block_out_channels: [64, 128, 256, 256, 512, 1024, 2048, 2048]
downsample_factors: [[1, 2], 2, 2, 2, 2, 2, 2, 2]
attn_blocks: [0, 0, 0, 0, 0, 0, 0, 0]
dropout: 0.0
ckpt:
resume_ckpt_path: ""
inference_ckpt_path: ./models/syncnet/latentsync_syncnet.pt # this pretrained model is from LatentSync (https://huggingface.co/ByteDance/LatentSync/tree/main)
save_ckpt_steps: 2500