Upload tokenizer
Browse files- README.md +1 -1
- special_tokens_map.json +4 -28
- tokenizer_config.json +0 -1
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
3 |
-
base_model: facebook/mms-1b-all
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
metrics:
|
7 |
- wer
|
8 |
model-index:
|
|
|
1 |
---
|
2 |
license: cc-by-nc-4.0
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: facebook/mms-1b-all
|
6 |
metrics:
|
7 |
- wer
|
8 |
model-index:
|
special_tokens_map.json
CHANGED
@@ -1,30 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "[PAD]",
|
18 |
-
"lstrip": true,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": true,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "[UNK]",
|
25 |
-
"lstrip": true,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": true,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer_config.json
CHANGED
@@ -39,7 +39,6 @@
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
42 |
-
"processor_class": "Wav2Vec2ProcessorWithLM",
|
43 |
"replace_word_delimiter_char": " ",
|
44 |
"target_lang": "krl",
|
45 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
39 |
"eos_token": "</s>",
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
"pad_token": "[PAD]",
|
|
|
42 |
"replace_word_delimiter_char": " ",
|
43 |
"target_lang": "krl",
|
44 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|