lgris commited on
Commit
6d7efd7
1 Parent(s): 2a1033c

Upload lm-boosted decoder

Browse files
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["", "<s>", "</s>", "\u2047", " ", "a", "e", "o", "s", "r", "i", "n", "m", "d", "t", "u", "c", "l", "p", "v", "q", "g", "f", "h", "b", "\u00e3", "\u00e9", "\u00e7", "\u00e1", "z", "j", "\u00ed", "\u00ea", "x", "\u00f3", "-", "\u00f5", "\u00fa", "\u00e0", "\u00f4", "\u00e2", "k", "y", "w"], "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/pt-4gram.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5988077751c5b3e96ae5fdfc8d913413f3bce307c85d0047c1a751eaa14b462f
3
+ size 4330633731
language_model/unigrams.txt ADDED
File without changes
preprocessor_config.json CHANGED
@@ -4,6 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0,
 
7
  "return_attention_mask": true,
8
  "sampling_rate": 16000
9
  }
 
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 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/a803f23f1afc428695542b16e67d92127ae59529b524e83b04b46e96c24e1dd5.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "lgris/bp_400h_xlsr2_300M", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}