Upload w2v2_lm

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 31,
+  "<s>": 30
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["w", "o", "k", "d", "r", "q", "c", "e", "y", "x", "n", "l", "t", "u", "'", "p", "i", "f", "z", "h", "b", "j", "s", "m", " ", "a", "v", "g", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

language_model/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db082c7e12cd5daae6375e0189c52b746482ff08afef4160097747d82dc28ff4
+size 1839642621

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

@@ -1,4 +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": "pongjin/en_with_korean_model_large_960h",
   "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/1c91466ccb7ea3e46923c53e0d16ee14184b0e8c2173d79b4b96a4f213d736be.fea372b8528a479b7415f13ca4e27a2f5f3782cbb3f15b4d19bb3cbe734e8137",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"