kingabzpro commited on
Commit
597f880
1 Parent(s): 9006a7e

Upload lm-boosted decoder

Browse files
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": [" ", "\u0621", "\u0622", "\u0623", "\u0624", "\u0625", "\u0626", "\u0627", "\u0628", "\u0629", "\u062a", "\u062b", "\u062c", "\u062d", "\u062e", "\u062f", "\u0630", "\u0631", "\u0632", "\u0633", "\u0634", "\u0635", "\u0636", "\u0637", "\u0638", "\u0639", "\u063a", "\u0641", "\u0642", "\u0643", "\u0644", "\u0645", "\u0646", "\u0647", "\u0648", "\u0649", "\u064a", "\u064e", "\u064f", "\u0650", "\u0652", "\u0686", "\u06a8", "\u06a9", "\u06be", "\u06cc", "\ufe83", "\ufefb", "\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 sha256:5fad0f448ae80ac42f87cdf1e25b27ce5fff0879223dd8ba9bdb65fbeae22f47
3
+ size 341947584
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
@@ -1 +1 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/root/.cache/huggingface/transformers/14798a531871933c4eb13fce05b7e19bde8b0dba3e77a948190c9c95f5c5804b.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "kingabzpro/wav2vec2-large-xlsr-300-arabic", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}