Training in progress, epoch 0

.gitignore

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

config.json

@@ -0,0 +1,212 @@
+{
+  "_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": "Arabic",
+    "1": "Basque",
+    "10": "Dutch",
+    "11": "English",
+    "12": "Esperanto",
+    "13": "Estonian",
+    "14": "French",
+    "15": "Frisian",
+    "16": "Georgian",
+    "17": "German",
+    "18": "Greek",
+    "19": "Hakha_Chin",
+    "2": "Breton",
+    "20": "Indonesian",
+    "21": "Interlingua",
+    "22": "Italian",
+    "23": "Japanese",
+    "24": "Kabyle",
+    "25": "Kinyarwanda",
+    "26": "Kyrgyz",
+    "27": "Latvian",
+    "28": "Maltese",
+    "29": "Mangolian",
+    "3": "Catalan",
+    "30": "Persian",
+    "31": "Polish",
+    "32": "Portuguese",
+    "33": "Romanian",
+    "34": "Romansh_Sursilvan",
+    "35": "Russian",
+    "36": "Sakha",
+    "37": "Slovenian",
+    "38": "Spanish",
+    "39": "Swedish",
+    "4": "Chinese_China",
+    "40": "Tamil",
+    "41": "Tatar",
+    "42": "Turkish",
+    "43": "Ukranian",
+    "44": "Welsh",
+    "5": "Chinese_Hongkong",
+    "6": "Chinese_Taiwan",
+    "7": "Chuvash",
+    "8": "Czech",
+    "9": "Dhivehi"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arabic": "0",
+    "Basque": "1",
+    "Breton": "2",
+    "Catalan": "3",
+    "Chinese_China": "4",
+    "Chinese_Hongkong": "5",
+    "Chinese_Taiwan": "6",
+    "Chuvash": "7",
+    "Czech": "8",
+    "Dhivehi": "9",
+    "Dutch": "10",
+    "English": "11",
+    "Esperanto": "12",
+    "Estonian": "13",
+    "French": "14",
+    "Frisian": "15",
+    "Georgian": "16",
+    "German": "17",
+    "Greek": "18",
+    "Hakha_Chin": "19",
+    "Indonesian": "20",
+    "Interlingua": "21",
+    "Italian": "22",
+    "Japanese": "23",
+    "Kabyle": "24",
+    "Kinyarwanda": "25",
+    "Kyrgyz": "26",
+    "Latvian": "27",
+    "Maltese": "28",
+    "Mangolian": "29",
+    "Persian": "30",
+    "Polish": "31",
+    "Portuguese": "32",
+    "Romanian": "33",
+    "Romansh_Sursilvan": "34",
+    "Russian": "35",
+    "Sakha": "36",
+    "Slovenian": "37",
+    "Spanish": "38",
+    "Swedish": "39",
+    "Tamil": "40",
+    "Tatar": "41",
+    "Turkish": "42",
+    "Ukranian": "43",
+    "Welsh": "44"
+  },
+  "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": "4.23.1",
+  "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:f5f37ce4889241fc78ebae6efb64350f985a218597a090f559f131b7f79175ee
+size 378392723

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adce4a4861a68c6800d3e3379c4e0a9b80c0b06b8a5fdce1ed690b3313457b87
+size 3375