Added language model

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "'", "-", "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"], "is_bpe": false}

language_model/4gram_lowercase_correct.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a0e9228a8f507e203a060dab371a36f823f929f2a4309c9061c7d2d6042df2
+size 102888102

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -4,7 +4,7 @@
  "feature_size": 1,
  "padding_side": "right",
  "padding_value": 0.0,
- "processor_class": "Wav2Vec2Processor",
+ "processor_class": "Wav2Vec2ProcessorWithLM",
  "return_attention_mask": true,
  "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
- "bos_token": "<s>",
- "eos_token": "</s>",
- "pad_token": "<pad>",
- "unk_token": "<unk>"
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<pad>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ },
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": true,
+ "normalized": false,
+ "rstrip": true,
+ "single_word": false
+ }
 }

tokenizer_config.json

@@ -39,7 +39,7 @@
  "eos_token": "</s>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<pad>",
- "processor_class": "Wav2Vec2Processor",
+ "processor_class": "Wav2Vec2ProcessorWithLM",
  "replace_word_delimiter_char": " ",
  "target_lang": null,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",