BlueV3 / configs /tts.json
notmax123's picture
Add files using upload-large-folder tool
0409b69 verified
Raw
History Blame Contribute Delete
9.43 kB
{
"tts_version": "v1.7.3",
"split": "opensource-multilingual",
"ae_ckpt_path": "checkpoints/44k_decoder/ae_541000.pt",
"ttl": {
"latent_dim": 24,
"chunk_compress_factor": 6,
"batch_expander": {
"n_batch_expand": 6
},
"normalizer": {
"scale": 0.25
},
"text_encoder": {
"n_langs": 0,
"lang_emb_dim": 0,
"text_embedder": {
"char_emb_dim": 256
},
"convnext": {
"idim": 256,
"ksz": 5,
"intermediate_dim": 1024,
"num_layers": 6,
"dilation_lst": [
1,
1,
2,
2,
4,
4
]
},
"attn_encoder": {
"hidden_channels": 256,
"filter_channels": 1024,
"n_heads": 4,
"n_layers": 4,
"p_dropout": 0.0
},
"proj_out": {
"idim": 256,
"odim": 256
}
},
"flow_matching": {
"sig_min": 1e-08
},
"nonverbal_tokens": {
"sample_weight": 10.0,
"loss_weight": 6.0,
"dataset_repeat": 8
},
"lang_sampling": {
"he": 10.0,
"en": 1.0,
"de": 1.0,
"it": 1.0,
"es": 1.0
},
"style_encoder": {
"proj_in": {
"ldim": 24,
"chunk_compress_factor": 6,
"odim": 256
},
"convnext": {
"idim": 256,
"ksz": 5,
"intermediate_dim": 1024,
"num_layers": 6,
"dilation_lst": [
1,
1,
1,
1,
1,
1
]
},
"style_token_layer": {
"input_dim": 256,
"n_style": 50,
"style_key_dim": 256,
"style_value_dim": 256,
"prototype_dim": 256,
"n_units": 256,
"n_heads": 2
}
},
"speech_prompted_text_encoder": {
"text_dim": 256,
"style_dim": 256,
"n_units": 256,
"n_heads": 2
},
"uncond_masker": {
"prob_both_uncond": 0.04,
"prob_text_uncond": 0.01,
"std": 0.1,
"text_dim": 256,
"n_style": 50,
"style_key_dim": 256,
"style_value_dim": 256
},
"vector_field": {
"n_langs": 0,
"lang_emb_dim": 0,
"proj_in": {
"ldim": 24,
"chunk_compress_factor": 6,
"odim": 512
},
"time_encoder": {
"time_dim": 64,
"hdim": 256
},
"main_blocks": {
"n_blocks": 4,
"time_cond_layer": {
"idim": 512,
"time_dim": 64
},
"style_cond_layer": {
"idim": 512,
"style_dim": 256
},
"text_cond_layer": {
"idim": 512,
"text_dim": 256,
"n_heads": 8,
"n_units": 512,
"use_residual": true,
"rotary_base": 10000,
"rotary_scale": 10
},
"convnext_0": {
"idim": 512,
"ksz": 5,
"intermediate_dim": 2048,
"num_layers": 4,
"dilation_lst": [
1,
2,
4,
8
]
},
"convnext_1": {
"idim": 512,
"ksz": 5,
"intermediate_dim": 2048,
"num_layers": 1,
"dilation_lst": [
1
]
},
"convnext_2": {
"idim": 512,
"ksz": 5,
"intermediate_dim": 2048,
"num_layers": 1,
"dilation_lst": [
1
]
}
},
"last_convnext": {
"idim": 512,
"ksz": 5,
"intermediate_dim": 2048,
"num_layers": 4,
"dilation_lst": [
1,
1,
1,
1
]
},
"proj_out": {
"idim": 512,
"chunk_compress_factor": 6,
"ldim": 24
},
"cfg_scale": 3.0
}
},
"ae": {
"data": {
"train_metadata": [
"/home/maxm/AE_training_data_all/slow_44K/data",
"/home/maxm/AE_training_data_all/datasets_4AE_extracted",
"/home/maxm/AE_training_data_all/AE_training_data",
"/home/maxm/AE_training_data_all/mls_spanish",
"/mnt/windows_nvme/ivrit/VoxKnesset-hebrew-ipa/clips"
],
"val_metadata": "filelists/val.csv",
"sample_rate": 44100,
"hop_length": 512,
"segment_size": 61740
},
"train": {
"batch_size": 128,
"gradient_accumulation_steps": 0,
"num_workers": 8,
"lr": 2e-04,
"save_interval": 1000,
"log_interval": 10
},
"sample_rate": 44100,
"n_delay": 0,
"base_chunk_size": 512,
"chunk_compress_factor": 1,
"ldim": 24,
"encoder": {
"spec_processor": {
"n_fft": 2048,
"win_length": 2048,
"hop_length": 512,
"n_mels": 228,
"sample_rate": 44100,
"eps": 1e-05,
"norm_mean": 0.0,
"norm_std": 1.0
},
"ksz_init": 7,
"ksz": 7,
"num_layers": 10,
"dilation_lst": [
1,
1,
1,
1,
1,
1,
1,
1,
1,
1
],
"intermediate_dim": 2048,
"idim": 1253,
"hdim": 512,
"odim": 24
},
"decoder": {
"ksz_init": 7,
"ksz": 7,
"num_layers": 10,
"dilation_lst": [
1,
2,
4,
1,
2,
4,
1,
1,
1,
1
],
"intermediate_dim": 2048,
"idim": 24,
"hdim": 512,
"head": {
"idim": 512,
"hdim": 2048,
"odim": 512,
"ksz": 3
}
}
},
"dp": {
"latent_dim": 24,
"chunk_compress_factor": 6,
"normalizer": {
"scale": 1.0
},
"sentence_encoder": {
"char_emb_dim": 64,
"text_embedder": {
"char_emb_dim": 64
},
"convnext": {
"idim": 64,
"ksz": 5,
"intermediate_dim": 256,
"num_layers": 6,
"dilation_lst": [
1,
1,
1,
1,
1,
1
]
},
"attn_encoder": {
"hidden_channels": 64,
"filter_channels": 256,
"n_heads": 2,
"n_layers": 2,
"p_dropout": 0.0
},
"proj_out": {
"idim": 64,
"odim": 64
}
},
"style_encoder": {
"proj_in": {
"ldim": 24,
"chunk_compress_factor": 6,
"odim": 64
},
"convnext": {
"idim": 64,
"ksz": 5,
"intermediate_dim": 256,
"num_layers": 4,
"dilation_lst": [
1,
1,
1,
1
]
},
"style_token_layer": {
"input_dim": 64,
"n_style": 8,
"style_key_dim": 0,
"style_value_dim": 16,
"prototype_dim": 64,
"n_units": 64,
"n_heads": 2
}
},
"predictor": {
"sentence_dim": 64,
"n_style": 8,
"style_dim": 16,
"hdim": 128,
"n_layer": 2
}
}
}