Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 109,
+  "<s>": 108
+}

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 256,
   "codevector_dim": 768,
@@ -53,14 +53,13 @@
   "feat_proj_dropout": 0.0,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
+  "hidden_dropout": 0.0,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.1,
+  "layerdrop": 0.0,
   "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.0,
@@ -78,7 +77,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 105,
+  "pad_token_id": 107,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -102,8 +101,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.30.2",
+  "transformers_version": "4.31.0.dev0",
   "use_weighted_layer_sum": false,
-  "vocab_size": 106,
+  "vocab_size": 110,
   "xvector_output_dim": 512
 }

preprocessor_config.json

@@ -3,7 +3,8 @@
   "feature_extractor_type": "Wav2Vec2FeatureExtractor",
   "feature_size": 1,
   "padding_side": "right",
-  "padding_value": 0.0,
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5184a28a77745e775de7517698661308ce5090d57c8ab62a923b790ece8ed1
-size 1262336429
+oid sha256:6f659c9a20b5d330d5b73a45c71b0e1becf93e1349578ac3a304019af8afbcfb
+size 1262352813

runs/Jun30_10-04-05_64df48378bb2/events.out.tfevents.1688120414.64df48378bb2.1419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018882fbff9f0b0de67d1635e3c4e7cce04fd3814968bdcdb421927f854516ef
+size 5845

special_tokens_map.json

@@ -1,4 +1,34 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -5,6 +5,7 @@
   "eos_token": "</s>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
   "replace_word_delimiter_char": " ",
   "target_lang": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f63e8248c90f82c8a0a9ea73e839432cfc0c7956368674a06d74ae0ea6ea517
-size 3963
+oid sha256:645a14c785ae828345ed6de887448e019cdae478f8e4270b5aa6a6943e08281f
+size 4027

vocab.json

@@ -1,108 +1,110 @@
 {
-  "0": 6,
-  "1": 82,
-  "2": 46,
-  "3": 88,
-  "4": 5,
-  "5": 25,
-  "6": 44,
-  "7": 18,
-  "8": 58,
-  "9": 40,
-  "[PAD]": 105,
-  "[UNK]": 104,
-  "a": 54,
-  "b": 67,
-  "c": 70,
-  "d": 17,
-  "e": 57,
-  "f": 102,
-  "g": 73,
-  "h": 21,
-  "i": 11,
-  "j": 36,
-  "k": 50,
-  "l": 22,
-  "m": 12,
-  "n": 81,
-  "o": 10,
-  "p": 90,
-  "q": 35,
-  "r": 3,
-  "s": 32,
-  "t": 29,
-  "u": 76,
-  "v": 43,
-  "w": 99,
-  "x": 16,
-  "y": 64,
-  "z": 93,
-  "|": 84,
-  "à": 78,
-  "á": 49,
-  "â": 38,
-  "ã": 69,
-  "è": 86,
-  "é": 28,
-  "ê": 94,
-  "ì": 59,
+  ",": 1,
+  ".": 2,
+  "0": 3,
+  "1": 4,
+  "2": 5,
+  "3": 6,
+  "4": 7,
+  "5": 8,
+  "6": 9,
+  "7": 10,
+  "8": 11,
+  "9": 12,
+  "[PAD]": 107,
+  "[UNK]": 106,
+  "a": 13,
+  "b": 14,
+  "c": 15,
+  "d": 16,
+  "e": 17,
+  "f": 18,
+  "g": 19,
+  "h": 20,
+  "i": 21,
+  "j": 22,
+  "k": 23,
+  "l": 24,
+  "m": 25,
+  "n": 26,
+  "o": 27,
+  "p": 28,
+  "q": 29,
+  "r": 30,
+  "s": 31,
+  "t": 32,
+  "u": 33,
+  "v": 34,
+  "w": 35,
+  "x": 36,
+  "y": 37,
+  "z": 38,
+  "|": 0,
+  "à": 39,
+  "á": 40,
+  "â": 41,
+  "ã": 42,
+  "è": 43,
+  "é": 44,
+  "ê": 45,
+  "ì": 46,
   "í": 47,
-  "ò": 103,
-  "ó": 100,
-  "ô": 8,
-  "õ": 62,
-  "ù": 74,
-  "ú": 52,
-  "ý": 65,
-  "ă": 60,
-  "đ": 75,
-  "ĩ": 91,
-  "ũ": 37,
-  "ơ": 97,
-  "ư": 71,
-  "ạ": 0,
-  "ả": 56,
-  "ấ": 39,
-  "ầ": 98,
-  "ẩ": 42,
-  "ẫ": 53,
-  "ậ": 95,
-  "ắ": 4,
-  "ằ": 1,
-  "ẳ": 31,
-  "ẵ": 63,
-  "ặ": 15,
-  "ẹ": 72,
-  "ẻ": 80,
-  "ẽ": 33,
-  "ế": 27,
-  "ề": 48,
-  "ể": 68,
-  "ễ": 51,
-  "ệ": 96,
-  "ỉ": 14,
-  "ị": 2,
-  "ọ": 23,
-  "ỏ": 83,
-  "ố": 66,
-  "ồ": 34,
-  "ổ": 77,
-  "ỗ": 41,
-  "ộ": 20,
-  "ớ": 55,
-  "ờ": 26,
-  "ở": 85,
-  "ỡ": 30,
-  "ợ": 87,
-  "ụ": 79,
-  "ủ": 45,
-  "ứ": 19,
-  "ừ": 24,
-  "ử": 61,
-  "ữ": 92,
-  "ự": 7,
-  "ỳ": 89,
-  "ỷ": 101,
-  "ỹ": 13,
-  "₫": 9
+  "ò": 48,
+  "ó": 49,
+  "ô": 50,
+  "õ": 51,
+  "ù": 52,
+  "ú": 53,
+  "ý": 54,
+  "ă": 55,
+  "đ": 56,
+  "ĩ": 57,
+  "ũ": 58,
+  "ơ": 59,
+  "ư": 60,
+  "ạ": 61,
+  "ả": 62,
+  "ấ": 63,
+  "ầ": 64,
+  "ẩ": 65,
+  "ẫ": 66,
+  "ậ": 67,
+  "ắ": 68,
+  "ằ": 69,
+  "ẳ": 70,
+  "ẵ": 71,
+  "ặ": 72,
+  "ẹ": 73,
+  "ẻ": 74,
+  "ẽ": 75,
+  "ế": 76,
+  "ề": 77,
+  "ể": 78,
+  "ễ": 79,
+  "ệ": 80,
+  "ỉ": 81,
+  "ị": 82,
+  "ọ": 83,
+  "ỏ": 84,
+  "ố": 85,
+  "ồ": 86,
+  "ổ": 87,
+  "ỗ": 88,
+  "ộ": 89,
+  "ớ": 90,
+  "ờ": 91,
+  "ở": 92,
+  "ỡ": 93,
+  "ợ": 94,
+  "ụ": 95,
+  "ủ": 96,
+  "ứ": 97,
+  "ừ": 98,
+  "ử": 99,
+  "ữ": 100,
+  "ự": 101,
+  "ỳ": 102,
+  "ỷ": 103,
+  "ỹ": 104,
+  "₫": 105
 }