Upload WanSpeechToVideoPipeline

transformer/diffusion_pytorch_model-00001-of-00007.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef76062a86c27dde52fc7c7f153ac63b1aa7792397e1991dcedf439ceb5a8ab
+oid sha256:a982f4454fbc5207dbe5cd417cdd538da08c800001c7d7c68adccb18897fc4d1
 size 4972707834

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -1227,18 +1227,18 @@
     "blocks.9.norm2.bias": "diffusion_pytorch_model-00002-of-00007.safetensors",
     "blocks.9.norm2.weight": "diffusion_pytorch_model-00002-of-00007.safetensors",
     "blocks.9.scale_shift_table": "diffusion_pytorch_model-00002-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv1_global.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv1_global.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv1_local.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv1_local.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv2.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv2.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv3.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.conv3.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.final_linear.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.final_linear.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.encoder.padding_tokens": "diffusion_pytorch_model-00001-of-00007.safetensors",
-    "condition_embedder.casual_audio_encoder.weights": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv1_global.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv1_global.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv1_local.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv1_local.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv2.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv2.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv3.conv.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.conv3.conv.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.final_linear.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.final_linear.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.encoder.padding_tokens": "diffusion_pytorch_model-00001-of-00007.safetensors",
+    "condition_embedder.causal_audio_encoder.weights": "diffusion_pytorch_model-00001-of-00007.safetensors",
     "condition_embedder.pose_embedder.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",
     "condition_embedder.pose_embedder.weight": "diffusion_pytorch_model-00001-of-00007.safetensors",
     "condition_embedder.text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00007.safetensors",