Upload lm-boosted decoder

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "$", "*", "+", "0", "1", "2", "3", "4", "5", "6", "7", "8", "9", "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", "\u00a0", "\u00a3", "\u00a5", "\u00e3", "\u00e9", "\u00ed", "\u00f3", "\u00fc", "\u0103", "\u0107", "\u015f", "\ufeff", "\u2047", ""], "is_bpe": false}

language_model/5-gram_xh.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e35e92eb003816779e07f9104f022c4b8fc5ab0c083237a3e8f51b85bb76c1c
+size 26089422

language_model/attrs.json

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

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

tokenizer_config.json

@@ -5,6 +5,7 @@
   "eos_token": null,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",