Training in progress, epoch 0

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,196 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "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,
+  "finetuning_task": "audio-classification",
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ck-xueya",
+    "1": "ck-xinlv",
+    "10": "ck-niaosuan",
+    "11": "ck-shuimian",
+    "12": "ck-diedao",
+    "13": "jj-huojiao",
+    "14": "fh-shouye",
+    "15": "dez-dianhua",
+    "16": "dxez-dianhua",
+    "17": "dxne-dianhua",
+    "18": "dne-dianhua",
+    "19": "bf-yinyue",
+    "2": "ck-maibo",
+    "20": "jr-shangcheng",
+    "21": "xz-keshi",
+    "22": "jk-zixun1",
+    "23": "y-yangshi",
+    "24": "jy-jiayuan",
+    "25": "jj-zhishiku",
+    "26": "jk-zixun2",
+    "27": "js-yundong",
+    "28": "dk-shouyinji",
+    "29": "dk-beiwanglu",
+    "3": "ck-tiwen",
+    "30": "dk-shipinlt",
+    "31": "ck-jk-baogao",
+    "32": "lx-kefu",
+    "33": "jdu-xindiantu",
+    "34": "kaideng",
+    "35": "guandeng",
+    "36": "un",
+    "4": "ck-xuyang",
+    "5": "ck-xuezhi",
+    "6": "ck-xutang",
+    "7": "ck-xindiantu",
+    "8": "ck-tizhi",
+    "9": "ck-tizhong"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bf-yinyue": "19",
+    "ck-diedao": "12",
+    "ck-jk-baogao": "31",
+    "ck-maibo": "2",
+    "ck-niaosuan": "10",
+    "ck-shuimian": "11",
+    "ck-tiwen": "3",
+    "ck-tizhi": "8",
+    "ck-tizhong": "9",
+    "ck-xindiantu": "7",
+    "ck-xinlv": "1",
+    "ck-xueya": "0",
+    "ck-xuezhi": "5",
+    "ck-xutang": "6",
+    "ck-xuyang": "4",
+    "dez-dianhua": "15",
+    "dk-beiwanglu": "29",
+    "dk-shipinlt": "30",
+    "dk-shouyinji": "28",
+    "dne-dianhua": "18",
+    "dxez-dianhua": "16",
+    "dxne-dianhua": "17",
+    "fh-shouye": "14",
+    "guandeng": "35",
+    "jdu-xindiantu": "33",
+    "jj-huojiao": "13",
+    "jj-zhishiku": "25",
+    "jk-zixun1": "22",
+    "jk-zixun2": "26",
+    "jr-shangcheng": "20",
+    "js-yundong": "27",
+    "jy-jiayuan": "24",
+    "kaideng": "34",
+    "lx-kefu": "32",
+    "un": "36",
+    "xz-keshi": "21",
+    "y-yangshi": "23"
+  },
+  "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": "4.30.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

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": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:952ce4acc92c1379785b7721a375e6742229647c0eee01be0c741b3be65842c7
+size 378386409

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4636797cb93ecbcd2efae0f44bf51829a829ec4f17a3da488df118320259cf
+size 3899