Upload lm-boosted decoder

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 52,
+  "<s>": 51
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["\u315c", "\u3152", "\u3141", "\u3160", "\u3143", "\u314c", "\u3158", "\u313c", "\u3138", "\u314b", "\u3136", "\u3135", "\u314a", "\u3148", "\u3144", "\u3149", "\u315e", "\u3151", "\u315b", "\u3131", " ", "\u3154", "\u3161", "\u3163", "\u314e", "\u3155", "\u313b", "\u3162", "\u3157", "\u3133", "\u314d", "\u3134", "\u3146", "\u3153", "\u3139", "\u315a", "\u315f", "\u3145", "\u3132", "\u3142", "\u3140", "\u3147", "\u313a", "\u3137", "\u315d", "\u3159", "\u3150", "\u314f", "\u3156", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90dd0d7198b1734fd70755114a3530823f3689bf91815b164208f51a3d6e7541
+size 17749133

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": false,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json

@@ -2,8 +2,11 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
+  "name_or_path": "NX2411/wav2vec2-large-xlsr-korean-demo-with-LM",
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/51a567f056bb60dc09ae81a627c2dd36ec1f24f8621a9a8da06d686b836c65f8.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"