|
{ |
|
"architectures": [ |
|
"MimiModel" |
|
], |
|
"attention_dropout": 0.0, |
|
"audio_channels": 1, |
|
"codebook_dim": 256, |
|
"codebook_size": 2048, |
|
"compress": 2, |
|
"dilation_growth_rate": 2, |
|
"frame_rate": 12.5, |
|
"head_dim": 64, |
|
"hidden_act": "gelu", |
|
"hidden_size": 512, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 2048, |
|
"kernel_size": 7, |
|
"last_kernel_size": 3, |
|
"layer_scale_initial_scale": 0.01, |
|
"max_position_embeddings": 8000, |
|
"model_type": "mimi", |
|
"norm_eps": 1e-05, |
|
"normalize": false, |
|
"num_attention_heads": 8, |
|
"num_filters": 64, |
|
"num_hidden_layers": 8, |
|
"num_key_value_heads": 8, |
|
"num_residual_layers": 1, |
|
"num_semantic_quantizers": 1, |
|
"pad_mode": "constant", |
|
"residual_kernel_size": 3, |
|
"rope_theta": 10000.0, |
|
"sampling_rate": 24000, |
|
"sliding_window": 250, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.45.0.dev0", |
|
"trim_right_ratio": 1.0, |
|
"upsample_groups": 512, |
|
"upsampling_ratios": [ |
|
8, |
|
6, |
|
5, |
|
4 |
|
], |
|
"use_cache": false, |
|
"use_causal_conv": true, |
|
"use_conv_shortcut": false, |
|
"vector_quantization_hidden_dimension": 256 |
|
} |
|
|