Commit
•
564a315
1
Parent(s):
cfcc186
Add LM
Browse files- 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 -1
- tokenizer_config.json +1 -1
alphabet.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"labels": ["\u0e37", "\u0e0a", "\u0e2e", "\u0e08", "\u0e31", "\u0e2b", "\u0e09", "\u0e04", "\u0e02", "\u0e06", "\u0e49", "\u0e27", "\u0e22", "\u0e2f", "\u0e43", "\u0e20", "\u0e23", "\u0e48", "\u0e14", "\u0e33", "\u0e42", "\u0e4b", "\u0e24", "\u0e0e", "\u0e45", "\u0e40", "\u0e16", "\u0e1c", "\u0e34", "\u0e13", "\u0e1a", "\u0e1d", "\u0e0c", "\u0e17", "\u0e15", "\u0e10", "\u0e11", "\u0e12", "\u0e28", "\u0e4a", "\u0e2c", "\u0e30", "\u0e41", "\u0e01", "\u0e47", "\u0e39", " ", "\u0e32", "\u0e0d", "\u0e18", "\u0e36", "\u0e07", "\u0e29", "\u0e35", "\u0e19", "\u0e25", "\u0e0b", "\u0e0f", "\u0e2a", "\u0e44", "\u0e38", "\u0e2d", "\u0e1e", "\u0e1f", "\u0e03", "\u0e1b", "\u0e21", "\u0e4c", "\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:c806efff1b63ec2bc31d7a89468dae4bdb1009d124f5736e8d9fc269d74c77a2
|
| 3 |
+
size 8799529
|
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": false,
|
| 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": false,
|
| 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}]}
|
|
|
|
| 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": "<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 +1 @@
|
|
| 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, "name_or_path": "./thai-asr-cv8", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
|
|
|
| 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, "name_or_path": "./thai-asr-cv8", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
|