skip audio loading if no audio in video (#1397)

diffsynth/core/data/operators.py

@@ -1,4 +1,4 @@
-import math
+import math, warnings
 import torch, torchvision, imageio, os
 import imageio.v3 as iio
 from PIL import Image
@@ -260,6 +260,7 @@ class LoadAudioWithTorchaudio(DataProcessingOperator, FrameSamplerByRateMixin):
         FrameSamplerByRateMixin.__init__(self, num_frames, time_division_factor, time_division_remainder, frame_rate, fix_frame_rate)
 
     def __call__(self, data: str):
+        try:
             reader = self.get_reader(data)
             num_frames = self.get_num_frames(reader)
             duration = num_frames / self.frame_rate
@@ -272,3 +273,6 @@ class LoadAudioWithTorchaudio(DataProcessingOperator, FrameSamplerByRateMixin):
                 padding = target_samples - current_samples
                 waveform = torch.nn.functional.pad(waveform, (0, padding))
             return waveform, sample_rate
+        except:
+            warnings.warn(f"Cannot load audio in {data}. The audio will be `None`.")
+            return None

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "diffsynth"
-version = "2.0.8"
+version = "2.0.9"
 description = "Enjoy the magic of Diffusion models!"
 authors = [{name = "ModelScope Team"}]
 license = {text = "Apache-2.0"}