whisper-dro-set2-dro / config.json
bartelds's picture
Upload dro model for set 2
415c0ce verified
{
"activation_dropout": 0.0,
"activation_function": "gelu",
"apply_spec_augment": false,
"architectures": [
"WhisperForConditionalGeneration"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": null,
"bos_token_id": 50257,
"classifier_proj_size": 256,
"d_model": 1280,
"decoder_attention_heads": 20,
"decoder_ffn_dim": 5120,
"decoder_layerdrop": 0.0,
"decoder_layers": 32,
"decoder_start_token_id": 50258,
"dro_state": {
"dro_q": [
0.11895060539245605,
0.26671966910362244,
0.16783207654953003,
0.13655038177967072,
0.1700296700000763,
0.13991765677928925
],
"groups": {
"0": "en",
"1": "fa",
"2": "hr",
"3": "it",
"4": "sk",
"5": "yue"
}
},
"dropout": 0.0,
"dtype": "float32",
"encoder_attention_heads": 20,
"encoder_ffn_dim": 5120,
"encoder_layerdrop": 0.0,
"encoder_layers": 32,
"eos_token_id": 50257,
"init_std": 0.02,
"is_encoder_decoder": true,
"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,
"max_length": null,
"max_source_positions": 1500,
"max_target_positions": 448,
"median_filter_width": 7,
"model_type": "whisper",
"num_hidden_layers": 32,
"num_mel_bins": 128,
"pad_token_id": 50256,
"scale_embedding": false,
"transformers_version": "4.57.1",
"use_cache": false,
"use_weighted_layer_sum": false,
"vocab_size": 51866
}