Commit
•
c8f2771
1
Parent(s):
d4cd795
Upload tokenizer
Browse files- special_tokens_map.json +18 -2
- tokenizer_config.json +3 -4
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,22 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
-
"pad_token": "
|
| 5 |
-
"unk_token": "
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "</s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
}
|
| 17 |
+
],
|
| 18 |
"bos_token": "<s>",
|
| 19 |
"eos_token": "</s>",
|
| 20 |
+
"pad_token": "[PAD]",
|
| 21 |
+
"unk_token": "[UNK]"
|
| 22 |
}
|
tokenizer_config.json
CHANGED
|
@@ -4,11 +4,10 @@
|
|
| 4 |
"do_lower_case": false,
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
-
"pad_token": "
|
| 8 |
-
"processor_class": "Wav2Vec2Processor",
|
| 9 |
"replace_word_delimiter_char": " ",
|
| 10 |
-
"target_lang": "
|
| 11 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 12 |
-
"unk_token": "
|
| 13 |
"word_delimiter_token": "|"
|
| 14 |
}
|
|
|
|
| 4 |
"do_lower_case": false,
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "[PAD]",
|
|
|
|
| 8 |
"replace_word_delimiter_char": " ",
|
| 9 |
+
"target_lang": "twi",
|
| 10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 11 |
+
"unk_token": "[UNK]",
|
| 12 |
"word_delimiter_token": "|"
|
| 13 |
}
|