config.json

{
  "_name_or_path": "KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru",
  "activation_dropout": 0.0,
  "adapter_attn_dim": null,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForSequenceClassification"
  ],
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoModelForAudioClassification": "KELONMYOSA/wav2vec2-xls-r-300m-emotion-ru--emotion_model.Wav2Vec2ForSpeechClassification"
  },
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 256,
  "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": true,
  "custom_pipelines": {
    "audio-classification": {
      "impl": "emotion_recognition_pipeline.SpeechEmotionRecognitionPipeline",
      "pt": [
        "AutoModelForAudioClassification"
      ],
      "tf": []
    }
  },
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": true,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_dropout": 0.0,
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.0,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.0,
  "finetuning_task": "wav2vec2_emotion_ru",
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "pingpong",
    "1": "caughing",
    "2": "clapping",
    "3": "silence"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "caughing": "1",
    "clapping": "2",
    "pingpong": "0",
    "silence": "3"
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "mask_channel_length": 10,
  "mask_channel_min_space": 1,
  "mask_channel_other": 0.0,
  "mask_channel_prob": 0.0,
  "mask_channel_selection": "static",
  "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_min_space": 1,
  "mask_time_other": 0.0,
  "mask_time_prob": 0.05,
  "mask_time_selection": "static",
  "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": 24,
  "num_negatives": 100,
  "output_hidden_size": 1024,
  "pad_token_id": 54,
  "problem_type": "single_label_classification",
  "proj_codevector_dim": 256,
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.37.0.dev0",
  "use_weighted_layer_sum": false,
  "vocab_size": 55,
  "xvector_output_dim": 512
}