[tests] fix clapconfig for text backbone in audioldm2 (huggingface#12490)

sayakpaul · web-flow · commit aed636f5f089 · 2025-10-15T10:57:09.000+05:30
fix clapconfig for text backbone in audioldm2
diff --git a/tests/pipelines/audioldm2/test_audioldm2.py b/tests/pipelines/audioldm2/test_audioldm2.py
@@ -138,10 +138,8 @@ def get_dummy_components(self):
             patch_stride=2,
             patch_embed_input_channels=4,
         )
-        text_encoder_config = ClapConfig.from_text_audio_configs(
-            text_config=text_branch_config,
-            audio_config=audio_branch_config,
-            projection_dim=16,
+        text_encoder_config = ClapConfig(
+            text_config=text_branch_config, audio_config=audio_branch_config, projection_dim=16
         )
         text_encoder = ClapModel(text_encoder_config)
         tokenizer = RobertaTokenizer.from_pretrained("hf-internal-testing/tiny-random-roberta", model_max_length=77)

Original file line number	Diff line number	Diff line change
`@@ -138,10 +138,8 @@ def get_dummy_components(self):`
`138`	`138`	`patch_stride=2,`
`139`	`139`	`patch_embed_input_channels=4,`
`140`	`140`	`)`
`141`		`- text_encoder_config = ClapConfig.from_text_audio_configs(`
`142`		`- text_config=text_branch_config,`
`143`		`- audio_config=audio_branch_config,`
`144`		`- projection_dim=16,`
	`141`	`+ text_encoder_config = ClapConfig(`
	`142`	`+ text_config=text_branch_config, audio_config=audio_branch_config, projection_dim=16`
`145`	`143`	`)`
`146`	`144`	`text_encoder = ClapModel(text_encoder_config)`
`147`	`145`	`tokenizer = RobertaTokenizer.from_pretrained("hf-internal-testing/tiny-random-roberta", model_max_length=77)`