{
  "architectures": [
    "PsarAIModel"
  ],
  "asr": {
    "activation_dropout": 0.05,
    "adapter_attn_dim": 16,
    "adapter_kernel_size": 3,
    "adapter_stride": 2,
    "add_adapter": false,
    "apply_spec_augment": true,
    "architectures": [
      "Wav2Vec2ForCTC"
    ],
    "attention_dropout": 0.05,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "classifier_proj_size": 256,
    "codevector_dim": 1024,
    "contrastive_logits_temperature": 0.1,
    "conv_bias": true,
    "conv_dim": [
      512,
      512,
      512,
      512,
      512,
      512,
      512
    ],
    "conv_kernel": [
      10,
      3,
      3,
      3,
      3,
      2,
      2
    ],
    "conv_stride": [
      5,
      2,
      2,
      2,
      2,
      2,
      2
    ],
    "ctc_loss_reduction": "mean",
    "ctc_zero_infinity": false,
    "diversity_loss_weight": 0.1,
    "do_stable_layer_norm": true,
    "dtype": "float32",
    "eos_token_id": 2,
    "feat_extract_activation": "gelu",
    "feat_extract_dropout": 0.0,
    "feat_extract_norm": "layer",
    "feat_proj_dropout": 0.05,
    "feat_quantizer_dropout": 0.0,
    "final_dropout": 0.05,
    "hidden_act": "gelu",
    "hidden_dropout": 0.05,
    "hidden_size": 1280,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 5120,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.05,
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_prob": 0.05,
    "model_type": "wav2vec2",
    "num_adapter_layers": 3,
    "num_attention_heads": 16,
    "num_codevector_groups": 2,
    "num_codevectors_per_group": 320,
    "num_conv_pos_embedding_groups": 16,
    "num_conv_pos_embeddings": 128,
    "num_feat_extract_layers": 7,
    "num_hidden_layers": 48,
    "num_negatives": 100,
    "output_attentions": false,
    "output_hidden_size": 1280,
    "output_hidden_states": false,
    "pad_token_id": 0,
    "problem_type": null,
    "proj_codevector_dim": 1024,
    "return_dict": true,
    "tdnn_dilation": [
      1,
      2,
      3,
      1,
      1
    ],
    "tdnn_dim": [
      512,
      512,
      512,
      512,
      1500
    ],
    "tdnn_kernel": [
      5,
      3,
      3,
      1,
      1
    ],
    "transformers_version": "5.20.2",
    "use_weighted_layer_sum": false,
    "vocab_size": 158,
    "xvector_output_dim": 512
  },
  "asr_adapters": {
    "auto": 158,
    "bridge": 153,
    "eng": 43,
    "fra": 60
  },
  "auto_map": {
    "AutoConfig": "modeling_psarai.PsarAIConfig",
    "AutoModel": "modeling_psarai.PsarAIModel"
  },
  "bridge": {
    "asr_dim": 1280,
    "asr_layers": 49,
    "mt_dim": 1024
  },
  "dtype": "float16",
  "model_type": "psarai_s2s",
  "mt": {
    "activation_dropout": 0.0,
    "activation_function": "relu",
    "architectures": [
      "M2M100ForConditionalGeneration"
    ],
    "attention_dropout": 0.1,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "d_model": 1024,
    "decoder_attention_heads": 16,
    "decoder_ffn_dim": 4096,
    "decoder_layerdrop": 0,
    "decoder_layers": 12,
    "decoder_start_token_id": 2,
    "dropout": 0.1,
    "dtype": "float32",
    "encoder_attention_heads": 16,
    "encoder_ffn_dim": 4096,
    "encoder_layerdrop": 0,
    "encoder_layers": 12,
    "eos_token_id": 2,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_std": 0.02,
    "is_encoder_decoder": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "max_position_embeddings": 1024,
    "model_type": "m2m_100",
    "output_attentions": false,
    "output_hidden_states": false,
    "pad_token_id": 1,
    "problem_type": null,
    "return_dict": true,
    "scale_embedding": true,
    "tie_word_embeddings": true,
    "tokenizer_class": "NllbTokenizer",
    "transformers_version": "5.20.2",
    "use_cache": false,
    "vocab_size": 256206
  },
  "sample_rate": 24000,
  "speak_languages": [
    "km",
    "en"
  ],
  "t2u": {
    "n_units": 1000,
    "speakers": 2
  },
  "transformers_version": "5.20.2",
  "vocoder": {
    "n_units": 1000
  }
}