Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 31,
+  "<s>": 30
+}

config.json

@@ -10,7 +10,7 @@
     "Wav2Vec2ForCTC"
   ],
   "attention_dropout": 0.1,
-  "bos_token_id": 1,
+  "bos_token_id": 30,
   "classifier_proj_size": 256,
   "codevector_dim": 256,
   "contrastive_logits_temperature": 0.1,
@@ -42,21 +42,18 @@
     2,
     2
   ],
-  "ctc_loss_reduction": "sum",
+  "ctc_loss_reduction": "mean",
   "ctc_zero_infinity": false,
   "diversity_loss_weight": 0.1,
   "do_stable_layer_norm": false,
-  "eos_token_id": 2,
+  "eos_token_id": 31,
   "feat_extract_activation": "gelu",
-  "feat_extract_dropout": 0.0,
   "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
+  "feat_proj_dropout": 0.0,
   "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,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -79,7 +76,7 @@
   "num_hidden_layers": 12,
   "num_negatives": 100,
   "output_hidden_size": 768,
-  "pad_token_id": 0,
+  "pad_token_id": 29,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b531f58a02080844df93e8f2e3f63bf9ce41d3a2c8f2c7f113aedd469d96e262
+oid sha256:1027b9f549fb4f5074a7a2ed2446d40d7bdeeac2465be0d7818eb759fa8c5f90
 size 377611120

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": false,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "28": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "31": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f0e329b99474ebfded05d5b6e99aeb2f0d7f7a82c158d6614ccbb123854c8e
+oid sha256:04870151b0266f9e4fe50fd0f5ca56fe5d3003aa0ee9fe2f62cfdc8f32fb5c33
 size 5112

vocab.json

@@ -0,0 +1,32 @@
+{
+  "'": 17,
+  "[PAD]": 29,
+  "[UNK]": 28,
+  "a": 14,
+  "b": 2,
+  "c": 6,
+  "d": 5,
+  "e": 11,
+  "f": 21,
+  "g": 9,
+  "h": 23,
+  "i": 8,
+  "j": 0,
+  "k": 20,
+  "l": 19,
+  "m": 13,
+  "n": 15,
+  "o": 25,
+  "p": 26,
+  "q": 22,
+  "r": 3,
+  "s": 16,
+  "t": 27,
+  "u": 18,
+  "v": 7,
+  "w": 12,
+  "x": 24,
+  "y": 10,
+  "z": 4,
+  "|": 1
+}