config.json

{
  "_name_or_path": "asapp/sew-d-mid-400k",
  "activation_dropout": 0.0,
  "apply_spec_augment": true,
  "architectures": [
    "SEWDForSequenceClassification"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "conv_bias": false,
  "conv_dim": [
    64,
    128,
    128,
    128,
    128,
    256,
    256,
    256,
    256,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    1,
    3,
    1,
    3,
    1,
    3,
    1,
    2,
    1,
    2,
    1
  ],
  "conv_stride": [
    5,
    2,
    1,
    2,
    1,
    2,
    1,
    2,
    1,
    2,
    1,
    2,
    1
  ],
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.1,
  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
  "final_dropout": 0.0,
  "finetuning_task": "audio-classification",
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 512,
  "id2label": {
    "0": "yes",
    "1": "no",
    "10": "_silence_",
    "11": "_unknown_",
    "2": "up",
    "3": "down",
    "4": "left",
    "5": "right",
    "6": "on",
    "7": "off",
    "8": "stop",
    "9": "go"
  },
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "label2id": {
    "_silence_": 10,
    "_unknown_": 11,
    "down": 3,
    "go": 9,
    "left": 4,
    "no": 1,
    "off": 7,
    "on": 6,
    "right": 5,
    "stop": 8,
    "up": 2,
    "yes": 0
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.2,
  "mask_feature_length": 10,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_prob": 0.65,
  "max_position_embeddings": 512,
  "model_type": "sew-d",
  "norm_rel_ebd": "layer_norm",
  "num_attention_heads": 8,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 31,
  "num_feat_extract_layers": 13,
  "num_hidden_layers": 24,
  "pad_token_id": 0,
  "pos_att_type": [
    "p2c",
    "c2p"
  ],
  "position_biased_input": false,
  "position_buckets": 256,
  "relative_attention": true,
  "share_att_key": true,
  "squeeze_factor": 2,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.12.0.dev0",
  "use_weighted_layer_sum": false,
  "vocab_size": 32
}