Commit
•
08c89b5
1
Parent(s):
a00787a
Upload lm-boosted decoder
Browse files- alphabet.json +1 -0
- language_model/5-gram_xh.bin +3 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- preprocessor_config.json +1 -0
- tokenizer_config.json +1 -0
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", "\u00a0", "\u00a3", "\u00a5", "\u00e3", "\u00e9", "\u00ed", "\u00f3", "\u00fc", "\u0103", "\u0107", "\u015f", "\ufeff", "\u2047", ""], "is_bpe": false}
|
language_model/5-gram_xh.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e35e92eb003816779e07f9104f022c4b8fc5ab0c083237a3e8f51b85bb76c1c
|
3 |
+
size 26089422
|
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 |
}
|
tokenizer_config.json
CHANGED
@@ -5,6 +5,7 @@
|
|
5 |
"eos_token": null,
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
|
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
10 |
"unk_token": "[UNK]",
|
|
|
5 |
"eos_token": null,
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
8 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
9 |
"replace_word_delimiter_char": " ",
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
11 |
"unk_token": "[UNK]",
|