config.json

{
  "architectures": [
    "SpeechEncoderDecoderModel"
  ],
  "bos_token_id": 0,
  "decoder": {
    "_name_or_path": "",
    "activation_dropout": 0.1,
    "activation_function": "relu",
    "add_cross_attention": true,
    "architectures": [
      "Speech2TextForConditionalGeneration"
    ],
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": 0.0,
    "conv_channels": 1024,
    "conv_kernel_sizes": [
      5,
      5
    ],
    "d_model": 256,
    "decoder_attention_heads": 4,
    "decoder_ffn_dim": 2048,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 7,
    "decoder_start_token_id": 2,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.1,
    "early_stopping": true,
    "encoder_attention_heads": 4,
    "encoder_ffn_dim": 2048,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 12,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_std": 0.02,
    "input_channels": 1,
    "input_feat_per_channel": 80,
    "is_decoder": true,
    "is_encoder_decoder": true,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 200,
    "max_source_positions": 6000,
    "max_target_positions": 1024,
    "min_length": 0,
    "model_type": "speech_to_text_2",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 5,
    "num_conv_layers": 2,
    "num_hidden_layers": 7,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_embedding": true,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.10.0.dev0",
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 10224
  },
  "encoder": {
    "_name_or_path": "",
    "activation_dropout": 0.1,
    "add_cross_attention": false,
    "apply_spec_augment": true,
    "architectures": [
      "Wav2Vec2ForPreTraining"
    ],
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "bos_token_id": 1,
    "chunk_size_feed_forward": 0,
    "codevector_dim": 768,
    "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": "sum",
    "ctc_zero_infinity": false,
    "decoder_start_token_id": null,
    "diversity_loss_weight": 0.1,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "do_stable_layer_norm": true,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "feat_extract_activation": "gelu",
    "feat_extract_dropout": 0.0,
    "feat_extract_norm": "layer",
    "feat_proj_dropout": 0.1,
    "feat_quantizer_dropout": 0.0,
    "final_dropout": 0.1,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "gradient_checkpointing": false,
    "hidden_act": "gelu",
    "hidden_dropout": 0.1,
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-05,
    "layerdrop": 0.1,
    "length_penalty": 1.0,
    "mask_feature_length": 10,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_prob": 0.05,
    "max_length": 20,
    "min_length": 0,
    "model_type": "wav2vec2",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "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,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "prefix": null,
    "problem_type": null,
    "proj_codevector_dim": 768,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.10.0.dev0",
    "use_bfloat16": false,
    "vocab_size": 32
  },
  "eos_token_id": 2,
  "feature_extractor_type": "wav2vec2",
  "is_encoder_decoder": true,
  "model_type": "speech-encoder-decoder",
  "pad_token_id": 1,
  "tie_word_embeddings": false,
  "tokenizer_class": "speech_to_text_2",
  "torch_dtype": "float32",
  "transformers_version": null,
  "num_beams": 4
}