File size: 2,552 Bytes
8eac705 | 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 | {
"model_type": "audiodit",
"sampling_rate": 24000,
"latent_hop": 2048,
"latent_dim": 64,
"max_wav_duration": 60,
"dit_dim": 2560,
"dit_depth": 32,
"dit_heads": 32,
"dit_ff_mult": 3.6,
"dit_bias": true,
"dit_eps": 1e-06,
"dit_dropout": 0.0,
"dit_adaln_type": "global",
"dit_adaln_use_text_cond": true,
"dit_cross_attn": true,
"dit_cross_attn_norm": false,
"dit_long_skip": true,
"dit_qk_norm": true,
"dit_text_conv": true,
"dit_text_dim": 768,
"dit_use_latent_condition": true,
"repa_dit_layer": 8,
"sigma": 0.0,
"text_encoder_model": "google/umt5-base",
"text_norm_feat": true,
"text_add_embed": true,
"text_encoder_config": {
"d_model": 768,
"d_ff": 2048,
"d_kv": 64,
"num_heads": 12,
"num_layers": 12,
"num_decoder_layers": 12,
"dropout_rate": 0.1,
"layer_norm_epsilon": 1e-06,
"relative_attention_num_buckets": 32,
"relative_attention_max_distance": 128,
"vocab_size": 256384,
"pad_token_id": 0,
"eos_token_id": 1,
"decoder_start_token_id": 0,
"_name_or_path": "ArthurZ/umt5-base",
"architectures": [
"UMT5ForConditionalGeneration"
],
"chunk_size_feed_forward": 0,
"classifier_dropout": 0.0,
"dense_act_fn": "gelu_new",
"dtype": "float32",
"feed_forward_proj": "gated-gelu",
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_factor": 1.0,
"is_decoder": false,
"is_encoder_decoder": true,
"is_gated_act": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"model_type": "umt5",
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"problem_type": null,
"return_dict": true,
"scalable_attention": true,
"tie_word_embeddings": true,
"tokenizer_class": "T5Tokenizer",
"use_cache": true
},
"vae_config": {
"in_channels": 1,
"channels": 128,
"c_mults": [
1,
2,
4,
8,
16
],
"strides": [
2,
4,
4,
8,
8
],
"latent_dim": 64,
"encoder_latent_dim": 128,
"use_snake": true,
"downsample_shortcut": "averaging",
"upsample_shortcut": "duplicating",
"out_shortcut": "averaging",
"in_shortcut": "duplicating",
"final_tanh": false,
"downsampling_ratio": 2048,
"sample_rate": 24000,
"scale": 0.71,
"model_type": "audiodit_vae"
},
"transformers_version": "5.3.0",
"quantization": {
"bits": 8,
"group_size": 64,
"mode": "affine"
}
}
|