cahya commited on
Commit
de8589e
1 Parent(s): 2ec76cd

add language model

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 40, "</s>": 41}
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", "\u00e2", "\u00e7", "\u00eb", "\u00ee", "\u00f6", "\u00fc", "\u011f", "\u0131", "\u015f", "\u0307", "\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 sha256:7a76859c96afc4fa223dc7e5cb4d000926ec82f25ffbf560afec88ad39ed8783
3
+ size 1831539
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 ADDED
@@ -0,0 +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": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
tokenizer_config.json ADDED
@@ -0,0 +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": "/home/cahya/.cache/huggingface/transformers/2916f85ca1c8db02f6dffab6c5680b457e26471b99cac401f31d9d01fd7af256.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "tokenizer_file": null, "name_or_path": "cahya/wav2vec2-base-turkish-artificial-cv", "processor_class": "Wav2Vec2ProcessorWithLM", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"-": 1, "a": 2, "b": 3, "c": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "q": 18, "r": 19, "s": 20, "t": 21, "u": 22, "v": 23, "w": 24, "x": 25, "y": 26, "z": 27, "â": 28, "ç": 29, "ë": 30, "î": 31, "ö": 32, "ü": 33, "ğ": 34, "ı": 35, "ş": 36, "̇": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}