0xb1
/

wav2vec2-base-finetuned-speech_commands-v0.02

Audio Classification

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

wav2vec2-base-finetuned-speech_commands-v0.02 / config.json

0xb1's picture

Training in progress, epoch 0

c99eb63 about 1 year ago

raw history blame contribute delete

No virus

3.72 kB

	{
	"_name_or_path": "0xb1/wav2vec2-base-finetuned-speech_commands-v0.02",
	"activation_dropout": 0.0,
	"adapter_kernel_size": 3,
	"adapter_stride": 2,
	"add_adapter": false,
	"apply_spec_augment": true,
	"architectures": [
	"Wav2Vec2ForSequenceClassification"
	],
	"attention_dropout": 0.1,
	"bos_token_id": 1,
	"classifier_proj_size": 256,
	"codevector_dim": 256,
	"contrastive_logits_temperature": 0.1,
	"conv_bias": false,
	"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,
	"diversity_loss_weight": 0.1,
	"do_stable_layer_norm": false,
	"eos_token_id": 2,
	"feat_extract_activation": "gelu",
	"feat_extract_norm": "group",
	"feat_proj_dropout": 0.1,
	"feat_quantizer_dropout": 0.0,
	"final_dropout": 0.0,
	"freeze_feat_extract_train": true,
	"hidden_act": "gelu",
	"hidden_dropout": 0.1,
	"hidden_size": 768,
	"id2label": {
	"0": "yes",
	"1": "no",
	"2": "up",
	"3": "down",
	"4": "left",
	"5": "right",
	"6": "on",
	"7": "off",
	"8": "stop",
	"9": "go",
	"10": "zero",
	"11": "one",
	"12": "two",
	"13": "three",
	"14": "four",
	"15": "five",
	"16": "six",
	"17": "seven",
	"18": "eight",
	"19": "nine",
	"20": "bed",
	"21": "bird",
	"22": "cat",
	"23": "dog",
	"24": "happy",
	"25": "house",
	"26": "marvin",
	"27": "sheila",
	"28": "tree",
	"29": "wow",
	"30": "backward",
	"31": "forward",
	"32": "follow",
	"33": "learn",
	"34": "visual",
	"35": "_silence_"
	},
	"initializer_range": 0.02,
	"intermediate_size": 3072,
	"label2id": {
	"_silence_": "35",
	"backward": "30",
	"bed": "20",
	"bird": "21",
	"cat": "22",
	"dog": "23",
	"down": "3",
	"eight": "18",
	"five": "15",
	"follow": "32",
	"forward": "31",
	"four": "14",
	"go": "9",
	"happy": "24",
	"house": "25",
	"learn": "33",
	"left": "4",
	"marvin": "26",
	"nine": "19",
	"no": "1",
	"off": "7",
	"on": "6",
	"one": "11",
	"right": "5",
	"seven": "17",
	"sheila": "27",
	"six": "16",
	"stop": "8",
	"three": "13",
	"tree": "28",
	"two": "12",
	"up": "2",
	"visual": "34",
	"wow": "29",
	"yes": "0",
	"zero": "10"
	},
	"layer_norm_eps": 1e-05,
	"layerdrop": 0.0,
	"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",
	"no_mask_channel_overlap": false,
	"no_mask_time_overlap": false,
	"num_adapter_layers": 3,
	"num_attention_heads": 12,
	"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": 12,
	"num_negatives": 100,
	"output_hidden_size": 768,
	"pad_token_id": 0,
	"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": "4.27.4",
	"use_weighted_layer_sum": false,
	"vocab_size": 32,
	"xvector_output_dim": 512
	}