deepgeek/MuseTalk
2
0
Fork 0
mirror of https://github.com/TMElyralab/MuseTalk.git synced 2026-02-04 17:39:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: windows infer & gradio (#312)

Browse Source 
* fix: windows infer

* docs: update readme

* docs: update readme

* feat: v1.5 gradio for windows&linux

* fix: dependencies

* feat: windows infer & gradio

---------

Co-authored-by: NeRF-Factory <zzhizhou66@gmail.com>
This commit is contained in:
Zhizhou Zhong
2025-04-12 23:22:22 +08:00
committed by GitHub
parent 36163fccbd
commit 67e7ee3c73
14 changed files with 613 additions and 245 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
musetalk/utils/audio_processor.py
View File

@@ -49,8 +49,9 @@ class AudioProcessor:
whisper_feature = []
# Process multiple 30s mel input features
for input_feature in whisper_input_features:
audio_feats = whisper.encoder(input_feature.to(device), output_hidden_states=True).hidden_states
audio_feats = torch.stack(audio_feats, dim=2).to(weight_dtype)
input_feature = input_feature.to(device).to(weight_dtype)
audio_feats = whisper.encoder(input_feature, output_hidden_states=True).hidden_states
audio_feats = torch.stack(audio_feats, dim=2)
whisper_feature.append(audio_feats)
whisper_feature = torch.cat(whisper_feature, dim=1)