End of training
Browse files- added_tokens.json +4 -0
- alphabet.json +1 -0
- language_model/attrs.json +1 -0
- language_model/scb_med_pobpad_corpus_newmm-5gram.bin +3 -0
- language_model/unigrams.txt +0 -0
- logs/events.out.tfevents.1675227901.e18ab16fa5fa.6769.0 +2 -2
- pytorch_model.bin +1 -1
- special_tokens_map.json +36 -0
- tokenizer_config.json +14 -0
- vocab.json +69 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 68,
|
3 |
+
"<s>": 67
|
4 |
+
}
|
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "\u0e01", "\u0e02", "\u0e04", "\u0e06", "\u0e07", "\u0e08", "\u0e09", "\u0e0a", "\u0e0b", "\u0e0c", "\u0e0d", "\u0e0e", "\u0e0f", "\u0e10", "\u0e11", "\u0e12", "\u0e13", "\u0e14", "\u0e15", "\u0e16", "\u0e17", "\u0e18", "\u0e19", "\u0e1a", "\u0e1b", "\u0e1c", "\u0e1d", "\u0e1e", "\u0e1f", "\u0e20", "\u0e21", "\u0e22", "\u0e23", "\u0e24", "\u0e25", "\u0e27", "\u0e28", "\u0e29", "\u0e2a", "\u0e2b", "\u0e2c", "\u0e2d", "\u0e2e", "\u0e30", "\u0e31", "\u0e32", "\u0e33", "\u0e34", "\u0e35", "\u0e36", "\u0e37", "\u0e38", "\u0e39", "\u0e40", "\u0e41", "\u0e42", "\u0e43", "\u0e44", "\u0e47", "\u0e48", "\u0e49", "\u0e4a", "\u0e4b", "\u0e4c", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
language_model/attrs.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
|
language_model/scb_med_pobpad_corpus_newmm-5gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b88b817998c5caae85ce44f0c4ee4edd5d8b44b72e4e994ee3b36667531c8810
|
3 |
+
size 316448195
|
language_model/unigrams.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
logs/events.out.tfevents.1675227901.e18ab16fa5fa.6769.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:594604eeed9749b8dbc679e72d6589deddf9e89c5337ae6257db09310485f2cb
|
3 |
+
size 22321
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262184749
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2862f771ca94c80a4d3b50e3a250225c475e0c7128c7a85d4a562584890a9b4e
|
3 |
size 1262184749
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"bos_token": "<s>",
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"pad_token": "[PAD]",
|
35 |
+
"unk_token": "[UNK]"
|
36 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"do_lower_case": false,
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "Botnoi/xls-r-300m-th-lm-v2",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
9 |
+
"replace_word_delimiter_char": " ",
|
10 |
+
"special_tokens_map_file": null,
|
11 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
12 |
+
"unk_token": "[UNK]",
|
13 |
+
"word_delimiter_token": "|"
|
14 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 66,
|
3 |
+
"[UNK]": 65,
|
4 |
+
"|": 0,
|
5 |
+
"ก": 1,
|
6 |
+
"ข": 2,
|
7 |
+
"ค": 3,
|
8 |
+
"ฆ": 4,
|
9 |
+
"ง": 5,
|
10 |
+
"จ": 6,
|
11 |
+
"ฉ": 7,
|
12 |
+
"ช": 8,
|
13 |
+
"ซ": 9,
|
14 |
+
"ฌ": 10,
|
15 |
+
"ญ": 11,
|
16 |
+
"ฎ": 12,
|
17 |
+
"ฏ": 13,
|
18 |
+
"ฐ": 14,
|
19 |
+
"ฑ": 15,
|
20 |
+
"ฒ": 16,
|
21 |
+
"ณ": 17,
|
22 |
+
"ด": 18,
|
23 |
+
"ต": 19,
|
24 |
+
"ถ": 20,
|
25 |
+
"ท": 21,
|
26 |
+
"ธ": 22,
|
27 |
+
"น": 23,
|
28 |
+
"บ": 24,
|
29 |
+
"ป": 25,
|
30 |
+
"ผ": 26,
|
31 |
+
"ฝ": 27,
|
32 |
+
"พ": 28,
|
33 |
+
"ฟ": 29,
|
34 |
+
"ภ": 30,
|
35 |
+
"ม": 31,
|
36 |
+
"ย": 32,
|
37 |
+
"ร": 33,
|
38 |
+
"ฤ": 34,
|
39 |
+
"ล": 35,
|
40 |
+
"ว": 36,
|
41 |
+
"ศ": 37,
|
42 |
+
"ษ": 38,
|
43 |
+
"ส": 39,
|
44 |
+
"ห": 40,
|
45 |
+
"ฬ": 41,
|
46 |
+
"อ": 42,
|
47 |
+
"ฮ": 43,
|
48 |
+
"ะ": 44,
|
49 |
+
"ั": 45,
|
50 |
+
"า": 46,
|
51 |
+
"ำ": 47,
|
52 |
+
"ิ": 48,
|
53 |
+
"ี": 49,
|
54 |
+
"ึ": 50,
|
55 |
+
"ื": 51,
|
56 |
+
"ุ": 52,
|
57 |
+
"ู": 53,
|
58 |
+
"เ": 54,
|
59 |
+
"แ": 55,
|
60 |
+
"โ": 56,
|
61 |
+
"ใ": 57,
|
62 |
+
"ไ": 58,
|
63 |
+
"็": 59,
|
64 |
+
"่": 60,
|
65 |
+
"้": 61,
|
66 |
+
"๊": 62,
|
67 |
+
"๋": 63,
|
68 |
+
"์": 64
|
69 |
+
}
|