From be656b199b62d2e8688ed0554c8b7ba4609e07d6 Mon Sep 17 00:00:00 2001
From: zzzweakman <zzzhong22@m.fudan.edu.cn>
Date: Sat, 12 Apr 2025 01:40:40 +0800
Subject: [PATCH] fix: dependencies

---
 README.md                     | 10 +++++-----
 app.py                        |  2 --
 requirements.txt              |  7 +++----
 scripts/realtime_inference.py |  2 +-
 4 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/README.md b/README.md
index d2c63df..e9059d9 100644
--- a/README.md
+++ b/README.md
@@ -177,11 +177,11 @@ pip install -r requirements.txt
 Install the MMLab ecosystem packages:
 
 ```bash
-pip install --no-cache-dir -U openmim 
-mim install mmengine 
-mim install "mmcv==2.0.1" 
-mim install "mmdet==3.1.0" 
-mim install "mmpose==1.1.0" 
+pip install --no-cache-dir -U openmim
+mim install mmengine
+mim install "mmcv==2.0.1"
+mim install "mmdet==3.1.0"
+mim install "mmpose==1.1.0"
 ```
 
 ### Setup FFmpeg
diff --git a/app.py b/app.py
index 716cea7..448e641 100644
--- a/app.py
+++ b/app.py
@@ -4,7 +4,6 @@ import pdb
 import re
 
 import gradio as gr
-import spaces
 import numpy as np
 import sys
 import subprocess
@@ -181,7 +180,6 @@ def fast_check_ffmpeg():
         return False
 
 
-@spaces.GPU(duration=600)
 @torch.no_grad()
 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)):
diff --git a/requirements.txt b/requirements.txt
index 1a7584a..e87aa41 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,21 +1,20 @@
 diffusers==0.30.2
 accelerate==0.28.0
+numpy==1.23.5
 tensorflow==2.12.0
 tensorboard==2.12.0
 opencv-python==4.9.0.80
 soundfile==0.12.1
 transformers==4.39.2
-huggingface_hub==0.25.0
+huggingface_hub==0.30.2
 librosa==0.11.0
-numpy==1.24.4
 einops==0.8.1
+gradio==5.24.0
 
 gdown
 requests
 imageio[ffmpeg]
 
-gradio
-spaces
 omegaconf
 ffmpeg-python
 moviepy
diff --git a/scripts/realtime_inference.py b/scripts/realtime_inference.py
index 5c547ef..4a12be7 100644
--- a/scripts/realtime_inference.py
+++ b/scripts/realtime_inference.py
@@ -327,7 +327,7 @@ if __name__ == "__main__":
     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_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("--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')