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

fix: dependencies

Browse Source
This commit is contained in:
zzzweakman
2025-04-12 01:40:40 +08:00
parent b9b459a119
commit be656b199b
4 changed files with 9 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
README.md
View File

@@ -177,11 +177,11 @@ pip install -r requirements.txt
Install the MMLab ecosystem packages: Install the MMLab ecosystem packages:
```bash ```bash
pip install --no-cache-dir -U openmim pip install --no-cache-dir -U openmim
mim install mmengine mim install mmengine
mim install "mmcv==2.0.1" mim install "mmcv==2.0.1"
mim install "mmdet==3.1.0" mim install "mmdet==3.1.0"
mim install "mmpose==1.1.0" mim install "mmpose==1.1.0"
``` ```
### Setup FFmpeg ### Setup FFmpeg

2
app.py
View File

@@ -4,7 +4,6 @@ import pdb
import re import re
import gradio as gr import gradio as gr
import spaces
import numpy as np import numpy as np
import sys import sys
import subprocess import subprocess
@@ -181,7 +180,6 @@ def fast_check_ffmpeg():
return False return False
@spaces.GPU(duration=600)
@torch.no_grad() @torch.no_grad()
def inference(audio_path, video_path, bbox_shift, extra_margin=10, parsing_mode="jaw", def inference(audio_path, video_path, bbox_shift, extra_margin=10, parsing_mode="jaw",
left_cheek_width=90, right_cheek_width=90, progress=gr.Progress(track_tqdm=True)): left_cheek_width=90, right_cheek_width=90, progress=gr.Progress(track_tqdm=True)):

7
requirements.txt
View File

@@ -1,21 +1,20 @@
diffusers==0.30.2 diffusers==0.30.2
accelerate==0.28.0 accelerate==0.28.0
numpy==1.23.5
tensorflow==2.12.0 tensorflow==2.12.0
tensorboard==2.12.0 tensorboard==2.12.0
opencv-python==4.9.0.80 opencv-python==4.9.0.80
soundfile==0.12.1 soundfile==0.12.1
transformers==4.39.2 transformers==4.39.2
huggingface_hub==0.25.0 huggingface_hub==0.30.2
librosa==0.11.0 librosa==0.11.0
numpy==1.24.4
einops==0.8.1 einops==0.8.1
gradio==5.24.0
gdown gdown
requests requests
imageio[ffmpeg] imageio[ffmpeg]
gradio
spaces
omegaconf omegaconf
ffmpeg-python ffmpeg-python
moviepy moviepy

2
scripts/realtime_inference.py
View File

@@ -327,7 +327,7 @@ if __name__ == "__main__":
parser.add_argument("--fps", type=int, default=25, help="Video frames per second") parser.add_argument("--fps", type=int, default=25, help="Video frames per second")
parser.add_argument("--audio_padding_length_left", type=int, default=2, help="Left padding length for audio") parser.add_argument("--audio_padding_length_left", type=int, default=2, help="Left padding length for audio")
parser.add_argument("--audio_padding_length_right", type=int, default=2, help="Right padding length for audio") parser.add_argument("--audio_padding_length_right", type=int, default=2, help="Right padding length for audio")
parser.add_argument("--batch_size", type=int, default=25, help="Batch size for inference") parser.add_argument("--batch_size", type=int, default=20, help="Batch size for inference")
parser.add_argument("--output_vid_name", type=str, default=None, help="Name of output video file") parser.add_argument("--output_vid_name", type=str, default=None, help="Name of output video file")
parser.add_argument("--use_saved_coord", action="store_true", help='Use saved coordinates to save time') parser.add_argument("--use_saved_coord", action="store_true", help='Use saved coordinates to save time')
parser.add_argument("--saved_coord", action="store_true", help='Save coordinates for future use') parser.add_argument("--saved_coord", action="store_true", help='Save coordinates for future use')