saattrupdan commited on
Commit
fc2c900
1 Parent(s): 461d536

Upload LM-boosted decoder

Browse files
alphabet.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"labels": ["t", "z", " ", "i", "n", "r", "g", "h", "f", "\u00e5", "\u00e9", "o", "w", "v", "j", "b", "\u00f3", "y", "\u00f8", "c", "d", "e", "m", "x", "k", "l", "\u00e6", "p", "u", "a", "s", "\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:c5ea8c4a370997de831c485a8993503c000710c9b1ff61b4d78b25f5140ce77d
3
+ size 1253607665
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
@@ -4,7 +4,7 @@
4
  "feature_size": 1,
5
  "padding_side": "right",
6
  "padding_value": 0.0,
7
- "processor_class": "Wav2Vec2Processor",
8
  "return_attention_mask": true,
9
  "sampling_rate": 16000
10
  }
 
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
 
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": "saattrupdan/voxpopuli-wav2vec2-large-cv8-da", "processor_class": "Wav2Vec2ProcessorWithLM", "tokenizer_class": "Wav2Vec2CTCTokenizer"}