config.json

{
  "architectures": [
    "Typhoon2Audio2AudioForConditionalGeneration"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_typhoon2audio.Typhoon2AudioConfig",
    "AutoModel": "modeling_typhoon2audio.Typhoon2Audio2AudioForConditionalGeneration"
  },
  "beats": {
    "model_type": ""
  },
  "ctc_decoder_config": "(4,4096,32,11008)",
  "ctc_loss_weight": 1.0,
  "ctc_upsample_factor": 25,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "intermediate_size": 14336,
  "llama_base_model": "scb10x/llama3.1-typhoon2-8b-instruct",
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "typhoon2audio",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 8.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "second_per_frame": 0.333333,
  "second_stride": 0.333333,
  "speech_decoder_ignore_index": -100,
  "speech_qformer_layer": 2,
  "speech_qformer_token_num": 1,
  "torch_dtype": "float16",
  "transformers_version": "4.45.0",
  "unit_vocab_size": 1000,
  "vocab_size": 128256,
  "vocoder_config": {
    "code_hop_size": 320,
    "dur_prediction_weight": 1.0,
    "dur_predictor_params": {
      "encoder_embed_dim": 512,
      "var_pred_dropout": 0.5,
      "var_pred_hidden_dim": 512,
      "var_pred_kernel_size": 3
    },
    "embedding_dim": 512,
    "hop_size": 256,
    "model_in_dim": 512,
    "n_fft": 1024,
    "num_embeddings": 1000,
    "num_freq": 1025,
    "num_mels": 80,
    "resblock": 1,
    "resblock_dilation_sizes": [
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ]
    ],
    "resblock_kernel_sizes": [
      3,
      7,
      11
    ],
    "sampling_rate": 16000,
    "segment_size": 8960,
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [
      11,
      8,
      8,
      4,
      4
    ],
    "upsample_rates": [
      5,
      4,
      4,
      2,
      2
    ],
    "win_size": 1024
  },
  "whisper": {
    "apply_spec_augment": true,
    "begin_suppress_tokens": [
      220,
      50257
    ],
    "bos_token_id": 50257,
    "d_model": 1280,
    "decoder_attention_heads": 20,
    "decoder_ffn_dim": 5120,
    "decoder_layers": 32,
    "decoder_start_token_id": 50258,
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layers": 32,
    "eos_token_id": 50257,
    "mask_feature_length": 64,
    "mask_feature_prob": 0.1,
    "mask_time_prob": 0.1,
    "max_length": 448,
    "model_type": "whisper",
    "num_hidden_layers": 32,
    "num_mel_bins": 128,
    "vocab_size": 51866
  },
  "whisper_extractor_feature_size": 128
}