Upload lm-boosted decoder
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 +10 -0
- special_tokens_map.json +14 -0
- tokenizer_config.json +1 -0
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "\u0981", "\u0982", "\u0983", "\u0985", "\u0986", "\u0987", "\u0988", "\u0989", "\u098a", "\u098b", "\u098f", "\u0990", "\u0993", "\u0994", "\u0995", "\u0996", "\u0997", "\u0998", "\u0999", "\u099a", "\u099b", "\u099c", "\u099d", "\u099e", "\u099f", "\u09a0", "\u09a1", "\u09a2", "\u09a3", "\u09a4", "\u09a5", "\u09a6", "\u09a7", "\u09a8", "\u09aa", "\u09ab", "\u09ac", "\u09ad", "\u09ae", "\u09af", "\u09b0", "\u09b2", "\u09b6", "\u09b7", "\u09b8", "\u09b9", "\u09be", "\u09bf", "\u09c0", "\u09c1", "\u09c2", "\u09c3", "\u09c7", "\u09c8", "\u09cb", "\u09cc", "\u09cd", "\u09ce", "\u09dc", "\u09dd", "\u09df", "\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:ea2fa769c2be7ef26f1b35cfd6f7d29684cc781eb7f0d469ddbccd7358136cd9
|
3 |
+
size 301267451
|
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
File without changes
|
preprocessor_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
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
@@ -1,5 +1,19 @@
|
|
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,
|
tokenizer_config.json
CHANGED
@@ -5,6 +5,7 @@
|
|
5 |
"eos_token": "</s>",
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
|
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"target_lang": null,
|
10 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
|
|
5 |
"eos_token": "</s>",
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "[PAD]",
|
8 |
+
"processor_class": "Wav2Vec2ProcessorWithLM",
|
9 |
"replace_word_delimiter_char": " ",
|
10 |
"target_lang": null,
|
11 |
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|