add tokenizer

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 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./Wav2vec_2H_060922/wav2vec2-librispeech-wolof",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "./Wav2vec_2H_060922/wav2vec2-librispeech-wolof/special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,39 @@
+{
+  "</s>": 34,
+  "<s>": 33,
+  "[PAD]": 36,
+  "[UNK]": 35,
+  "a": 32,
+  "b": 7,
+  "c": 2,
+  "d": 5,
+  "e": 18,
+  "f": 29,
+  "g": 21,
+  "h": 17,
+  "i": 4,
+  "j": 24,
+  "k": 11,
+  "l": 0,
+  "m": 13,
+  "n": 22,
+  "o": 3,
+  "p": 26,
+  "q": 12,
+  "r": 9,
+  "s": 6,
+  "t": 20,
+  "u": 1,
+  "v": 31,
+  "w": 19,
+  "x": 8,
+  "y": 25,
+  "|": 15,
+  "à": 28,
+  "ã": 30,
+  "ç": 14,
+  "é": 10,
+  "ë": 27,
+  "ñ": 16,
+  "ó": 23
+}