crossdelenna
commited on
Commit
•
c944ca0
1
Parent(s):
98cf19e
Upload lm-boosted decoder
Browse files- added_tokens.json +1 -0
- alphabet.json +1 -0
- language_model/3gram.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +1 -0
- special_tokens_map.json +1 -6
- tokenizer_config.json +1 -10
- vocab.json +1 -32
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<s>": 30, "</s>": 31}
|
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": ["s", "n", "y", "o", "t", "l", "r", "k", "w", "c", "v", "g", "h", "z", "'", "m", "a", "e", "u", "i", "q", " ", "b", "j", "p", "f", "x", "d", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
|
language_model/3gram.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:761824bf3b24ecc641c50f1b43073e7cea0854cbe5c3bccf7c1ff4d0e7e51f0e
|
3 |
+
size 10419611
|
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/unigrams.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
CHANGED
@@ -4,6 +4,7 @@
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
|
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
"padding_value": 0.0,
|
7 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
8 |
"return_attention_mask": true,
|
9 |
"sampling_rate": 16000
|
10 |
}
|
special_tokens_map.json
CHANGED
@@ -1,6 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"eos_token": "</s>",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"unk_token": "[UNK]"
|
6 |
-
}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
@@ -1,10 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"do_lower_case": false,
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"pad_token": "[PAD]",
|
6 |
-
"replace_word_delimiter_char": " ",
|
7 |
-
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
8 |
-
"unk_token": "[UNK]",
|
9 |
-
"word_delimiter_token": "|"
|
10 |
-
}
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": "/root/.cache/huggingface/transformers/f260852cdc917ea96f4c3e190c02d8e56bfc4b959b5160d503d135ab05754df1.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137", "name_or_path": "crossdelenna/wav2vec2-base-eng-ind", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
CHANGED
@@ -1,32 +1 @@
|
|
1 |
-
{
|
2 |
-
"'": 14,
|
3 |
-
"[PAD]": 29,
|
4 |
-
"[UNK]": 28,
|
5 |
-
"a": 16,
|
6 |
-
"b": 22,
|
7 |
-
"c": 9,
|
8 |
-
"d": 27,
|
9 |
-
"e": 17,
|
10 |
-
"f": 25,
|
11 |
-
"g": 11,
|
12 |
-
"h": 12,
|
13 |
-
"i": 19,
|
14 |
-
"j": 23,
|
15 |
-
"k": 7,
|
16 |
-
"l": 5,
|
17 |
-
"m": 15,
|
18 |
-
"n": 1,
|
19 |
-
"o": 3,
|
20 |
-
"p": 24,
|
21 |
-
"q": 20,
|
22 |
-
"r": 6,
|
23 |
-
"s": 0,
|
24 |
-
"t": 4,
|
25 |
-
"u": 18,
|
26 |
-
"v": 10,
|
27 |
-
"w": 8,
|
28 |
-
"x": 26,
|
29 |
-
"y": 2,
|
30 |
-
"z": 13,
|
31 |
-
"|": 21
|
32 |
-
}
|
|
|
1 |
+
{"'": 14, "[PAD]": 29, "[UNK]": 28, "a": 16, "b": 22, "c": 9, "d": 27, "e": 17, "f": 25, "g": 11, "h": 12, "i": 19, "j": 23, "k": 7, "l": 5, "m": 15, "n": 1, "o": 3, "p": 24, "q": 20, "r": 6, "s": 0, "t": 4, "u": 18, "v": 10, "w": 8, "x": 26, "y": 2, "z": 13, "|": 21}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|