Upload tokenizer

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+base_model: facebook/wav2vec2-base
 metrics:
 - wer
 model-index:

added_tokens.json

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

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": "|"
+}

vocab.json

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