Quentin Meeus
training 1600 steps slue-voxpopuli combined labels
3434a94
{
"_name_or_path": "openai/whisper-small",
"activation_dropout": 0.0,
"activation_function": "gelu",
"adaptor_activation": "relu",
"adaptor_init": "constant",
"adaptor_layernorm": true,
"architectures": [
"WhisperForTokenClassification"
],
"attention_dropout": 0.0,
"begin_suppress_tokens": [
220,
50257
],
"bos_token_id": 50257,
"crf_transition_matrix": null,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 50258,
"dropout": 0.0,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 50257,
"forced_decoder_ids": null,
"init_std": 0.02,
"is_encoder_decoder": true,
"max_length": 448,
"max_source_positions": 1500,
"max_target_positions": 448,
"model_type": "whisper_for_slu",
"num_hidden_layers": 12,
"num_mel_bins": 80,
"pad_token_id": 50257,
"scale_embedding": false,
"slu_attention_heads": 4,
"slu_dropout": 0.0,
"slu_embed_dim": 256,
"slu_ffn_dim": 2048,
"slu_focus": 1.0,
"slu_input_from": "decoder",
"slu_input_layers": [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11
],
"slu_layers": 2,
"slu_max_positions": null,
"slu_output_dim": 15,
"slu_pad_token_id": 1,
"slu_start_token_id": 36,
"slu_task": "named_entity_recognition",
"slu_weight": 1.0,
"task": "token_classification",
"torch_dtype": "float32",
"transformers_version": "4.26.0.dev0",
"use_cache": true,
"vocab_size": 51865
}