Upload tokenizer
Browse files- special_tokens_map.json +6 -0
- tokenizer_config.json +12 -0
- vocab.json +1 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "[UNK]"
|
| 6 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"replace_word_delimiter_char": " ",
|
| 9 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 10 |
+
"unk_token": "[UNK]",
|
| 11 |
+
"word_delimiter_token": "|"
|
| 12 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"y": 0, "i": 1, "n": 2, "c": 3, "u": 4, "p": 5, "t": 6, "x": 7, "s": 8, "z": 9, "j": 10, "r": 11, "w": 12, "b": 13, "l": 14, "f": 15, "a": 16, "q": 17, "m": 18, "e": 19, "o": 20, "'": 21, "v": 22, "k": 23, "h": 24, "d": 25, "g": 26, "|": 27, "[UNK]": 28, "[PAD]": 29}
|