Text-to-Speech
Safetensors
GGUF
English
voxtream
zero-shot
streaming
voxtream2.5 / config.json
herimor's picture
Initial commit
22a30f3 verified
Raw History Blame Contribute Delete
921 Bytes
{
"phone_former": "phone_former",
"temp_former": "temp_former",
"dep_former": "dep_former",
"audio_vocab_size": 2050,
"audio_pad_size": 0,
"embedding_dim": 1024,
"spk_embedding_dim": 192,
"num_codebooks": 32,
"num_phone_states": 6,
"amortization_divisor": 4,
"max_look_ahead": 5,
"audio_window_size": 625,
"phone_window_size": 625,
"phone_root_vocab_size": 62,
"phone_attr_vocab_sizes": [
3,
2,
5,
2
],
"phone_la_weights": [
0.25,
0.15,
0.15,
0.15,
0.3
],
"train_prompt_sink": true,
"dep_former_head": "mog",
"mog_codebook_size": 2048,
"mog_latent_dim": 256,
"mog_num_components": 1024,
"mog_low_rank": 64,
"mog_num_layers": 3,
"mog_intermediate_dim": 4096,
"mog_min_log_std": -4.0,
"mog_label_smoothing": 0.01,
"mog_ar_levels": 3
}