ashesicsis1
commited on
Commit
•
185c9b6
1
Parent(s):
856a49c
commit files to HF hub
Browse files- alphabet.json +1 -0
- language_model/5gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +11 -0
- special_tokens_map.json +28 -0
- tokenizer_config.json +3 -1
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
language_model/5gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2b15c479141d06a5fab8b50378663dd55aecb5f38a028c9a6777ee52307793c
|
3 |
+
size 3921919482
|
language_model/attrs.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"alpha": 0.5, "beta": 1.0, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/unigrams.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"ignore_mismatched_sizes": true,
|
6 |
+
"padding_side": "right",
|
7 |
+
"padding_value": 0.0,
|
8 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
9 |
+
"return_attention_mask": true,
|
10 |
+
"sampling_rate": 16000
|
11 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,5 +1,33 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
{
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
|
|
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 |
+
"content": "<s>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "</s>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
{
|
32 |
"content": "<s>",
|
33 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -2,11 +2,13 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
-
"name_or_path": "
|
6 |
"pad_token": "[PAD]",
|
|
|
7 |
"replace_word_delimiter_char": " ",
|
8 |
"special_tokens_map_file": null,
|
9 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
10 |
"unk_token": "[UNK]",
|
11 |
"word_delimiter_token": "|"
|
12 |
}
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
+
"name_or_path": "/content/drive/MyDrive/CAAD/dataset/large_tokenizer-lv60/",
|
6 |
"pad_token": "[PAD]",
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
+
"tokenizer_file": null,
|
12 |
"unk_token": "[UNK]",
|
13 |
"word_delimiter_token": "|"
|
14 |
}
|