Training in progress, epoch 1

config.json

@@ -0,0 +1,172 @@
+{
+  "_name_or_path": "ntu-spml/distilhubert",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": false,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": false,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "DoAumentada",
+    "1": "DoDisminuida",
+    "10": "LaBemolDisminuida",
+    "11": "LaBemolMayor",
+    "12": "LaBemolMenor",
+    "13": "LaDisminuida",
+    "14": "LaMayor",
+    "15": "LaMenor",
+    "16": "MiAumentada",
+    "17": "MiBemolAumentada",
+    "18": "MiBemolDisminuida",
+    "19": "MiBemolMayor",
+    "2": "DoMayor",
+    "20": "MiBemolMenor",
+    "21": "MiDisminuida",
+    "22": "MiMayor",
+    "23": "MiMenor",
+    "24": "ReAumentada",
+    "25": "ReBemolAumentada",
+    "26": "ReBemolDisminuida",
+    "27": "ReBemolMayor",
+    "28": "ReBemolMenor",
+    "29": "ReDisminuida",
+    "3": "DoMenor",
+    "30": "ReMayor",
+    "31": "ReMenor",
+    "32": "SiAumentada",
+    "33": "SiBemolAumentada",
+    "34": "SiBemolDisminuida",
+    "35": "SiBemolMayor",
+    "36": "SiBemolMenor",
+    "37": "SiDisminuida",
+    "38": "SiMayor",
+    "39": "SiMenor",
+    "4": "FaAumentada",
+    "40": "SolAumentada",
+    "41": "SolBemolAumentada",
+    "42": "SolBemolDisminuida",
+    "43": "SolBemolMayor",
+    "44": "SolBemolMenor",
+    "45": "SolDisminuida",
+    "46": "SolMayor",
+    "47": "SolMenor",
+    "5": "FaDisminuida",
+    "6": "FaMayor",
+    "7": "FaMenor",
+    "8": "LaAumentada",
+    "9": "LaBemolAumentada"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "DoAumentada": "0",
+    "DoDisminuida": "1",
+    "DoMayor": "2",
+    "DoMenor": "3",
+    "FaAumentada": "4",
+    "FaDisminuida": "5",
+    "FaMayor": "6",
+    "FaMenor": "7",
+    "LaAumentada": "8",
+    "LaBemolAumentada": "9",
+    "LaBemolDisminuida": "10",
+    "LaBemolMayor": "11",
+    "LaBemolMenor": "12",
+    "LaDisminuida": "13",
+    "LaMayor": "14",
+    "LaMenor": "15",
+    "MiAumentada": "16",
+    "MiBemolAumentada": "17",
+    "MiBemolDisminuida": "18",
+    "MiBemolMayor": "19",
+    "MiBemolMenor": "20",
+    "MiDisminuida": "21",
+    "MiMayor": "22",
+    "MiMenor": "23",
+    "ReAumentada": "24",
+    "ReBemolAumentada": "25",
+    "ReBemolDisminuida": "26",
+    "ReBemolMayor": "27",
+    "ReBemolMenor": "28",
+    "ReDisminuida": "29",
+    "ReMayor": "30",
+    "ReMenor": "31",
+    "SiAumentada": "32",
+    "SiBemolAumentada": "33",
+    "SiBemolDisminuida": "34",
+    "SiBemolMayor": "35",
+    "SiBemolMenor": "36",
+    "SiDisminuida": "37",
+    "SiMayor": "38",
+    "SiMenor": "39",
+    "SolAumentada": "40",
+    "SolBemolAumentada": "41",
+    "SolBemolDisminuida": "42",
+    "SolBemolMayor": "43",
+    "SolBemolMenor": "44",
+    "SolDisminuida": "45",
+    "SolMayor": "46",
+    "SolMenor": "47"
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 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:bd0ad2e30d311d822fcf43cc48973a9e39434cafef72045b234b8c9cedae43ed
+size 94822480

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4e84b2f6740f7d75b65adbb54b36365be3b8b1e9d00caa53581599a1d7cb64
+size 4091