File size: 3,527 Bytes
a1d788f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 | {
"_attn_implementation_autoset": false,
"acoustic_tokenizer_config": {
"causal": true,
"channels": 1,
"conv_bias": true,
"conv_norm": "none",
"corpus_normalize": 0.0,
"decoder_depths": null,
"decoder_n_filters": 32,
"decoder_ratios": [
8,
5,
5,
4,
2,
2
],
"disable_last_norm": true,
"dtype": "bfloat16",
"encoder_depths": "3-3-3-3-3-3-8",
"encoder_n_filters": 32,
"encoder_ratios": [
8,
5,
5,
4,
2,
2
],
"fix_std": 0.5,
"layer_scale_init_value": 1e-06,
"layernorm": "RMSNorm",
"layernorm_elementwise_affine": true,
"layernorm_eps": 1e-05,
"mixer_layer": "depthwise_conv",
"model_type": "vibevoice_acoustic_tokenizer",
"pad_mode": "constant",
"std_dist_type": "gaussian",
"vae_dim": 64,
"weight_init_value": 0.01
},
"acoustic_vae_dim": 64,
"architectures": [
"VibeVoiceForASRTraining"
],
"decoder_config": {
"attention_dropout": 0.0,
"dtype": "bfloat16",
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 65536,
"max_window_layers": 28,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
},
"diffusion_head_config": {
"ddpm_batch_mul": 4,
"ddpm_beta_schedule": "cosine",
"ddpm_num_inference_steps": 20,
"ddpm_num_steps": 1000,
"diffusion_type": "ddpm",
"head_ffn_ratio": 3.0,
"head_layers": 4,
"hidden_size": 1536,
"latent_size": 64,
"model_type": "vibepod_diffusion_head",
"prediction_type": "v_prediction",
"rms_norm_eps": 1e-05,
"speech_vae_dim": 64
},
"dtype": "float32",
"model_type": "vibevoice",
"semantic_tokenizer_config": {
"causal": true,
"channels": 1,
"conv_bias": true,
"conv_norm": "none",
"corpus_normalize": 0.0,
"disable_last_norm": true,
"dtype": "bfloat16",
"encoder_depths": "3-3-3-3-3-3-8",
"encoder_n_filters": 32,
"encoder_ratios": [
8,
5,
5,
4,
2,
2
],
"fix_std": 0,
"layer_scale_init_value": 1e-06,
"layernorm": "RMSNorm",
"layernorm_elementwise_affine": true,
"layernorm_eps": 1e-05,
"mixer_layer": "depthwise_conv",
"model_type": "vibevoice_semantic_tokenizer",
"pad_mode": "constant",
"std_dist_type": "none",
"vae_dim": 128,
"weight_init_value": 0.01
},
"semantic_vae_dim": 128,
"transformers_version": "4.57.6"
}
|