Hugging Face's logo

Spaces:
gholapeajinkya
/
DubSync
Sleeping

App Files Community
2
gholapeajinkya commited on
Commit
7d2b33c
·
verified ·
1 Parent(s): 40bf6d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -8,7 +8,7 @@ app_port: 8501
8
  tags:
9
  - streamlit
10
  pinned: false
11
- short_description: Welcome to DubSync! Transform your videos with AI-powered du
12
  ---
13
  # DubSync
14
 
@@ -136,4 +136,10 @@ streamlit run app.py
136
  | `medium` | Slower | High | ~769 MB |
137
  | `large` | Slowest | Highest | ~1.55 GB |
138
  | `large-v2` | Slowest | Highest | ~1.55 GB |
139
- | `large-v3` | Slowest | Highest | ~1.55 GB |
 
 
 
 
 
 
 
8
  tags:
9
  - streamlit
10
  pinned: false
11
+ short_description: Video dubbing with voice & emotion preserved
12
  ---
13
  # DubSync
14
 
 
136
  | `medium` | Slower | High | ~769 MB |
137
  | `large` | Slowest | Highest | ~1.55 GB |
138
  | `large-v2` | Slowest | Highest | ~1.55 GB |
139
+ | `large-v3` | Slowest | Highest | ~1.55 GB |
140
+
141
+ ## 🚀 Why Need a GPU
142
+
143
+ - **Demucs** is used for vocal/music separation — very slow on CPU.
144
+ - **F5-TTS** is used for multilingual emotional voice cloning — takes several minutes per line without GPU.
145
+ - Users to experience seamless dubbing under 5 minutes per video, which is only possible with GPU acceleration.