s2-pro / config.json
SummerSmile's picture
Duplicate from fishaudio/s2-pro
ce0ace9
{
"audio_decoder_config": {
"attention_o_bias": false,
"attention_qk_norm": false,
"attention_qkv_bias": false,
"audio_hidden_dim": 5120,
"dim": 2560,
"dropout": 0.0,
"head_dim": 128,
"initializer_range": 0.01976423537605237,
"intermediate_size": 9728,
"max_seq_len": 11,
"model_type": "fish_qwen3_audio_decoder",
"moe_intermediate_size": 768,
"n_head": 32,
"n_layer": 4,
"n_local_heads": 8,
"norm_eps": 1e-06,
"norm_topk_prob": true,
"num_codebooks": 10,
"num_experts": 1,
"num_experts_per_tok": 1,
"rope_base": 1000000,
"router_gamma": 0.001,
"text_dim": 2560,
"tie_word_embeddings": false,
"use_aux_loss_free": false,
"use_bfloat16": false,
"use_gradient_checkpointing": true,
"use_moe": false,
"vocab_size": 4096
},
"audio_pad_token_id": 151677,
"dtype": "bfloat16",
"eos_token_id": 151645,
"model_type": "fish_qwen3_omni",
"pad_token_id": 151669,
"semantic_end_token_id": 155773,
"semantic_start_token_id": 151678,
"text_config": {
"attention_o_bias": false,
"attention_qk_norm": true,
"attention_qkv_bias": false,
"audio_hidden_dim": 5120,
"dim": 2560,
"dropout": 0.0,
"head_dim": 128,
"initializer_range": 0.01976423537605237,
"intermediate_size": 9728,
"max_seq_len": 32768,
"model_type": "fish_qwen3",
"moe_intermediate_size": 768,
"n_head": 32,
"n_layer": 36,
"n_local_heads": 8,
"norm_eps": 1e-06,
"norm_topk_prob": true,
"num_experts": 1,
"num_experts_per_tok": 1,
"rope_base": 1000000,
"router_gamma": 0.001,
"tie_word_embeddings": true,
"use_aux_loss_free": false,
"use_bfloat16": false,
"use_gradient_checkpointing": true,
"use_moe": false,
"vocab_size": 155776
},
"transformers_version": "4.57.1"
}