Upload lm-boosted decoder

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/unigrams.txt filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "#", "'", "+", "-", "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", "\u00df", "\u00e0", "\u00e1", "\u00e2", "\u00e3", "\u00e4", "\u00e7", "\u00e8", "\u00e9", "\u00ea", "\u00eb", "\u00ee", "\u00ef", "\u00f2", "\u00f3", "\u00f4", "\u00f6", "\u00f8", "\u00fa", "\u00fb", "\u00fc", "\u00ff", "\u0131", "\u0142", "\u0144", "\u014d", "\u0153", "\u0159", "\u015f", "\u0161", "\u016b", "\u0175", "\u0177", "\u0259", "\u03b1", "\u201e", "\u5954", "\u718a", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/attrs.json

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

language_model/lm.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4748720ec004c8eca2e2c0b2614b01762acb83a142a7a073fff7e0350844b23a
+size 3041598527

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f1f4f553563531a1c4f85d5b2508694e8ee252677e5b4e16caea5648a2f5ae
+size 12013016

preprocessor_config.json

@@ -4,7 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0,
-  "processor_class": "Wav2Vec2Processor",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

tokenizer_config.json

@@ -43,7 +43,7 @@
   "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",