Training in progress, epoch 0

config.json

@@ -0,0 +1,151 @@
+{
+ "_name_or_path": "facebook/wav2vec2-base",
+ "activation_dropout": 0.0,
+ "adapter_attn_dim": null,
+ "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,
+ "finetuning_task": "audio-classification",
+ "freeze_feat_extract_train": true,
+ "hidden_act": "gelu",
+ "hidden_dropout": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "abroad",
+ "1": "address",
+ "10": "high_value_payment",
+ "11": "joint_account",
+ "12": "latest_transactions",
+ "13": "pay_bill",
+ "2": "app_error",
+ "3": "atm_limit",
+ "4": "balance",
+ "5": "business_loan",
+ "6": "card_issues",
+ "7": "cash_deposit",
+ "8": "direct_debit",
+ "9": "freeze"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "abroad": "0",
+ "address": "1",
+ "app_error": "2",
+ "atm_limit": "3",
+ "balance": "4",
+ "business_loan": "5",
+ "card_issues": "6",
+ "cash_deposit": "7",
+ "direct_debit": "8",
+ "freeze": "9",
+ "high_value_payment": "10",
+ "joint_account": "11",
+ "latest_transactions": "12",
+ "pay_bill": "13"
+ },
+ "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": "4.33.0.dev0",
+ "use_weighted_layer_sum": false,
+ "vocab_size": 32,
+ "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d1cb162560f43c8a6d6af17f502c5e7e5be4405c38d1b3697c7fd4ee143341
+size 378314656

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+ "do_normalize": true,
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+ "feature_size": 1,
+ "padding_side": "right",
+ "padding_value": 0.0,
+ "return_attention_mask": true,
+ "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84cd0231a5fdaeb7e0c5d22be9680c986a2e626c42d00855876284dd6b77d84
+size 4219