BeigeTTS / config.json
isaiahintelliga's picture
Upload BeigeTTS - Research release for neural speech synthesis (CC BY-NC 4.0)
d28be92 verified
{
"architectures": [
"GemmaForCausalLM"
],
"boi_token_index": 255999,
"eoi_token_index": 256000,
"eos_token_id": 107,
"image_token_index": 262144,
"initializer_range": 0.02,
"mm_tokens_per_image": 256,
"model_type": "gemma",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_logit_softcapping": null,
"cache_implementation": "hybrid",
"final_logit_softcapping": null,
"head_dim": 256,
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 10240,
"max_position_embeddings": 131072,
"model_type": "gemma3_text",
"num_attention_heads": 8,
"num_hidden_layers": 34,
"num_key_value_heads": 4,
"query_pre_attn_scalar": 256,
"rms_norm_eps": 1e-06,
"rope_local_base_freq": 10000.0,
"rope_scaling": {
"factor": 8.0,
"rope_type": "linear"
},
"rope_theta": 1000000.0,
"sliding_window": 1024,
"sliding_window_pattern": 6,
"torch_dtype": "bfloat16",
"use_cache": true,
"vocab_size": 327690
},
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"vision_config": {
"attention_dropout": 0.0,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 896,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 27,
"patch_size": 14,
"torch_dtype": "bfloat16",
"vision_use_head": false
},
"model_name": "BeigeTTS",
"model_variant": "research_release",
"production_model": "Khaki_TTS",
"vocab_size": 327690,
"hidden_size": 3584,
"intermediate_size": 14336,
"num_hidden_layers": 40,
"num_attention_heads": 16,
"num_key_value_heads": 8,
"head_dim": 256,
"hidden_act": "gelu_pytorch_tanh",
"max_position_embeddings": 8192,
"rms_norm_eps": 1e-06,
"pad_token_id": 0,
"bos_token_id": 106,
"tie_word_embeddings": true,
"rope_theta": 10000.0,
"attention_bias": false,
"attention_dropout": 0.0,
"audio_config": {
"audio_start_token": 262145,
"audio_end_token": 262146,
"neucodec_offset": 262154,
"neucodec_vocab_size": 65536,
"sample_rate": 24000,
"codec": "neucodec",
"supported_languages": [
"en"
],
"production_languages": 57,
"max_duration_seconds": 10,
"production_max_duration": "unlimited"
},
"license": "cc-by-nc-4.0",
"organization": "BlandAI"
}