Training in progress, epoch 0

.gitignore

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

config.json

@@ -0,0 +1,184 @@
+{
+  "_name_or_path": "asapp/sew-mid-100k",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SEWForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    64,
+    128,
+    128,
+    128,
+    128,
+    256,
+    256,
+    256,
+    256,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    1,
+    3,
+    1,
+    3,
+    1,
+    3,
+    1,
+    2,
+    1,
+    2,
+    1
+  ],
+  "conv_stride": [
+    5,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "final_dropout": 0.0,
+  "finetuning_task": "audio-classification",
+  "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": 0.2,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.65,
+  "model_type": "sew",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 31,
+  "num_feat_extract_layers": 13,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "squeeze_factor": 2,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.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": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434178bf400c9028f62967b373411cf6bf1b5db3e436c24553ba960b6ecaf5cc
+size 699695619

runs/Oct28_09-11-12_anton-gpu-v100/1635412294.3535721/events.out.tfevents.1635412294.anton-gpu-v100.796941.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a733b2242784e19d71848c08f72eb9088d83034e2b5de2bdcd25bc220c1eb5
+size 4578

runs/Oct28_09-11-12_anton-gpu-v100/events.out.tfevents.1635412294.anton-gpu-v100.796941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a21327d6e677e0553ecd8d76665cba9ca514ca3e8c1ab54a0646e2f571566422
+size 9109

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e58d0f50c43f8ce463c2b845d1696b42a52243528a771ba16f2f7003b170d989
+size 2927