| { |
| "architectures": [ |
| "Usad2Model" |
| ], |
| "attention_dropout_p": 0.0, |
| "attention_type": "mhsa", |
| "auto_map": { |
| "AutoConfig": "configuration_usad2.Usad2Config", |
| "AutoModel": "modeling_usad2.Usad2Model" |
| }, |
| "conv_dropout_p": 0.0, |
| "conv_expansion_factor": 2, |
| "conv_kernel_size": 31, |
| "conv_pos": true, |
| "conv_pos_depth": 5, |
| "conv_pos_groups": 16, |
| "conv_pos_width": 95, |
| "conv_subsample_channels": 64, |
| "conv_subsample_rate": 2, |
| "encoder_dim": 1024, |
| "feed_forward_dropout_p": 0.0, |
| "feed_forward_expansion_factor": 4, |
| "half_step_residual": true, |
| "input_dim": 128, |
| "input_dropout_p": 0.0, |
| "layerdrop_p": 0.0, |
| "model_type": "usad2", |
| "num_attention_heads": 16, |
| "num_layers": 24, |
| "patch_size_freq": 16, |
| "patch_size_time": 16, |
| "pre_norm": true, |
| "rms_norm": false, |
| "sample_rate": 16000, |
| "subsample_normalization": true, |
| "torch_dtype": "float32", |
| "transformer_style": true, |
| "transformers_version": "4.49.0", |
| "usad_v2": true, |
| "use_framewise_subsample": true, |
| "use_patchwise_subsample": false |
| } |
|
|
