| { | |
| "architectures": [ | |
| "SERModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "pipeline_utils.SERConfig", | |
| "AutoModelForAudioClassification": "pipeline_utils.SERModel" | |
| }, | |
| "id2label": { | |
| "0": "arousal", | |
| "1": "dominance", | |
| "2": "valence" | |
| }, | |
| "sampling_rate": 16000, | |
| "maxlen": 192000, | |
| "mean": -8.278621631819787e-05, | |
| "std": 0.08485510250851999, | |
| "classifier_dropout_prob": 0.5, | |
| "classifier_hidden_layers": 1, | |
| "hidden_size": 1024, | |
| "model_type": "ser", | |
| "num_attention_heads": 16, | |
| "num_classes": 3, | |
| "num_hidden_layers": 24, | |
| "ssl_type": "microsoft/wavlm-large", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.0.dev0" | |
| } | |