leviethoang
commited on
Commit
•
a464225
1
Parent(s):
467675c
Upload lm-boosted decoder
Browse files- alphabet.json +1 -0
- language_model/attrs.json +1 -0
- language_model/unigrams.txt +0 -0
- language_model/vi_lm_5grams.bin +3 -0
- preprocessor_config.json +1 -0
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
alphabet.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"labels": [" ", "'", "<", ">", "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", "\u00e0", "\u00e1", "\u00e2", "\u00e3", "\u00e8", "\u00e9", "\u00ea", "\u00ec", "\u00ed", "\u00f2", "\u00f3", "\u00f4", "\u00f5", "\u00f9", "\u00fa", "\u00fd", "\u0103", "\u0111", "\u0129", "\u0169", "\u01a1", "\u01b0", "\u1ea1", "\u1ea3", "\u1ea5", "\u1ea7", "\u1ea9", "\u1eab", "\u1ead", "\u1eaf", "\u1eb1", "\u1eb3", "\u1eb5", "\u1eb7", "\u1eb9", "\u1ebb", "\u1ebd", "\u1ebf", "\u1ec1", "\u1ec3", "\u1ec5", "\u1ec7", "\u1ec9", "\u1ecb", "\u1ecd", "\u1ecf", "\u1ed1", "\u1ed3", "\u1ed5", "\u1ed7", "\u1ed9", "\u1edb", "\u1edd", "\u1edf", "\u1ee1", "\u1ee3", "\u1ee5", "\u1ee7", "\u1ee9", "\u1eeb", "\u1eed", "\u1eef", "\u1ef1", "\u1ef3", "\u1ef5", "\u1ef7", "\u1ef9", "\u2047", "[<pad>", "<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/unigrams.txt
ADDED
File without changes
|
language_model/vi_lm_5grams.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2e3e3264950427d249876ac3dd24c0f506b06f1cca3e2c4095e0f95e50b3133
|
3 |
+
size 2471072676
|
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 +1 @@
|
|
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}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
|
|
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}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "ai-project/wav2vec2-large-xls-r-300m-
|
|
|
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": null, "tokenizer_file": null, "name_or_path": "ai-project/wav2vec2-large-xls-r-300m-group8-50p", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
|