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/5gram_correct.arpa filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["*", "b", "i", "j", "q", "\u0255", "\u0263", "\u026c", "\u0290", "\u0430", "\u0431", "\u0432", "\u0435", "\u0438", "\u0439", "\u043c", "\u043d", "\u043e", "\u0440", "\u0441", "\u0443", "\u0447", "\u0448", "\u044b", "\u044d", "\u044e", "\u0451", "\u049b", "\u04ad", "\u04b3", "\u04b5", "\u04e1", "\u0525", "\u10f6", "\u2047", "", "<s>", "</s>", " "], "is_bpe": false}

language_model/5gram_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0f2a75318c5192d2b9ecdb3c47bbff0eac7905f99ed4719151a6d0ec3b0941
+size 63706271

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
 }

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": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "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

@@ -40,6 +40,7 @@
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
   "target_lang": "kbd",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",