feat: windows infer & gradio (#312)

* 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>

scripts/inference.py

@@ -8,9 +8,11 @@ import shutil
 import pickle
 import argparse
 import numpy as np
+import subprocess
 from tqdm import tqdm
 from omegaconf import OmegaConf
 from transformers import WhisperModel
+import sys
 
 from musetalk.utils.blending import get_image
 from musetalk.utils.face_parsing import FaceParsing
@@ -18,16 +20,26 @@ from musetalk.utils.audio_processor import AudioProcessor
 from musetalk.utils.utils import get_file_type, get_video_fps, datagen, load_all_model
 from musetalk.utils.preprocessing import get_landmark_and_bbox, read_imgs, coord_placeholder
 
+def fast_check_ffmpeg():
+    try:
+        subprocess.run(["ffmpeg", "-version"], capture_output=True, check=True)
+        return True
+    except:
+        return False
+
 @torch.no_grad()
 def main(args):
     # Configure ffmpeg path
-    if args.ffmpeg_path not in os.getenv('PATH'):
+    if not fast_check_ffmpeg():
         print("Adding ffmpeg to PATH")
-        os.environ["PATH"] = f"{args.ffmpeg_path}:{os.environ['PATH']}"
+        # Choose path separator based on operating system
+        path_separator = ';' if sys.platform == 'win32' else ':'
+        os.environ["PATH"] = f"{args.ffmpeg_path}{path_separator}{os.environ['PATH']}"
+        if not fast_check_ffmpeg():
+            print("Warning: Unable to find ffmpeg, please ensure ffmpeg is properly installed")
     
     # Set computing device
     device = torch.device(f"cuda:{args.gpu_id}" if torch.cuda.is_available() else "cpu")
-    
     # Load model weights
     vae, unet, pe = load_all_model(
         unet_model_path=args.unet_model_path, 

scripts/preprocess.py

@@ -12,11 +12,23 @@ from mmpose.structures import merge_data_samples
 import torch
 import numpy as np
 from tqdm import tqdm
+import sys
+
+def fast_check_ffmpeg():
+    try:
+        subprocess.run(["ffmpeg", "-version"], capture_output=True, check=True)
+        return True
+    except:
+        return False
 
 ffmpeg_path = "./ffmpeg-4.4-amd64-static/"
-if ffmpeg_path not in os.getenv('PATH'):
-    print("add ffmpeg to path")
-    os.environ["PATH"] = f"{ffmpeg_path}:{os.environ['PATH']}"
+if not fast_check_ffmpeg():
+    print("Adding ffmpeg to PATH")
+    # Choose path separator based on operating system
+    path_separator = ';' if sys.platform == 'win32' else ':'
+    os.environ["PATH"] = f"{args.ffmpeg_path}{path_separator}{os.environ['PATH']}"
+    if not fast_check_ffmpeg():
+        print("Warning: Unable to find ffmpeg, please ensure ffmpeg is properly installed")
 
 class AnalyzeFace:
     def __init__(self, device: Union[str, torch.device], config_file: str, checkpoint_file: str):

scripts/realtime_inference.py

@@ -23,6 +23,15 @@ import shutil
 import threading
 import queue
 import time
+import subprocess
+
+
+def fast_check_ffmpeg():
+    try:
+        subprocess.run(["ffmpeg", "-version"], capture_output=True, check=True)
+        return True
+    except:
+        return False
 
 
 def video2imgs(vid_path, save_path, ext='.png', cut_frame=10000000):
@@ -318,7 +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')
@@ -332,6 +341,15 @@ if __name__ == "__main__":
 
     args = parser.parse_args()
 
+    # Configure ffmpeg path
+    if not fast_check_ffmpeg():
+        print("Adding ffmpeg to PATH")
+        # Choose path separator based on operating system
+        path_separator = ';' if sys.platform == 'win32' else ':'
+        os.environ["PATH"] = f"{args.ffmpeg_path}{path_separator}{os.environ['PATH']}"
+        if not fast_check_ffmpeg():
+            print("Warning: Unable to find ffmpeg, please ensure ffmpeg is properly installed")
+
     # Set computing device
     device = torch.device(f"cuda:{args.gpu_id}" if torch.cuda.is_available() else "cpu")