Training in progress, epoch 1

config.json

@@ -0,0 +1,172 @@
+{
+  "_name_or_path": "OthmaneJ/distil-wav2vec2",
+  "activation_dropout": 0.1,
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "People  and  Blogs",
+    "1": "Business",
+    "10": "N/A",
+    "11": "Comedy",
+    "12": "News  and  Politics",
+    "13": "Sports",
+    "14": "Arts",
+    "15": "Science  and  Technology",
+    "16": "Autos  and  Vehicles",
+    "17": "Science and Technology",
+    "18": "People and Blogs",
+    "19": "Music",
+    "2": "Nonprofits  and  Activism",
+    "20": "Society and Culture",
+    "21": "Education",
+    "22": "Howto  and  Style",
+    "23": "Film  and  Animation",
+    "24": "Gaming",
+    "25": "Entertainment",
+    "26": "Travel  and  Events",
+    "27": "Health and Fitness",
+    "28": "audiobook",
+    "3": "Crime",
+    "4": "History",
+    "5": "Pets  and  Animals",
+    "6": "News and Politics",
+    "7": "Travel and Events",
+    "8": "Kids and Family",
+    "9": "Leisure"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arts": "14",
+    "Autos  and  Vehicles": "16",
+    "Business": "1",
+    "Comedy": "11",
+    "Crime": "3",
+    "Education": "21",
+    "Entertainment": "25",
+    "Film  and  Animation": "23",
+    "Gaming": "24",
+    "Health and Fitness": "27",
+    "History": "4",
+    "Howto  and  Style": "22",
+    "Kids and Family": "8",
+    "Leisure": "9",
+    "Music": "19",
+    "N/A": "10",
+    "News  and  Politics": "12",
+    "News and Politics": "6",
+    "Nonprofits  and  Activism": "2",
+    "People  and  Blogs": "0",
+    "People and Blogs": "18",
+    "Pets  and  Animals": "5",
+    "Science  and  Technology": "15",
+    "Science and Technology": "17",
+    "Society and Culture": "20",
+    "Sports": "13",
+    "Travel  and  Events": "26",
+    "Travel and Events": "7",
+    "audiobook": "28"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "wav2vec2",
+  "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": 6,
+  "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": "4.33.2",
+  "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": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c3b5aaea1f3e6952d7516a3bf0fe6f03900a127d36c3767bf1b7267848dd6b
+size 208235881

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af6a2fed6ce87f85bbdb67eb556df3fa20121a6741a407dac14dbf7247ed05a
+size 4091