Upload lm-boosted decoder

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 17,
+  "<s>": 16
+}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "#", "1", "2", "3", "4", "5", "a", "b", "c", "d", "e", "f", "g", "\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/unigrams.txt

@@ -0,0 +1,91 @@
+</s>
+<s>
+a#2
+a#2.
+a#3
+a#3.
+a#4
+a#4.
+a#5
+a#5.
+a1
+a1.
+a2
+a2.
+a3
+a3.
+a4
+a4.
+a5
+b2
+b2.
+b3
+b3.
+b4
+b4.
+b5
+c#3
+c#3.
+c#4
+c#4.
+c#5
+c#5.
+c3
+c3.
+c4
+c4.
+c5
+c5.
+d#3
+d#3.
+d#4
+d#4.
+d#5
+d#5.
+d2
+d3
+d3.
+d4
+d4.
+d5
+d5.
+e2
+e2.
+e3
+e3.
+e4
+e4.
+e5
+e5.
+f#2
+f#2.
+f#3
+f#3.
+f#4
+f#4.
+f#5
+f#5.
+f1
+f2
+f3
+f3.
+f4
+f4.
+f5
+f5.
+g#2
+g#2.
+g#3
+g#3.
+g#4
+g#4.
+g#5
+g#5.
+g2
+g2.
+g3
+g3.
+g4
+g4.
+g5
+g5.

special_tokens_map.json

@@ -0,0 +1,78 @@
+{
+  "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
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "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]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "gary109/ai-light-dance_singing_ft_wav2vec2-large-xlsr-53-5gram",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,18 @@
+{
+  "#": 1,
+  "1": 2,
+  "2": 3,
+  "3": 4,
+  "4": 5,
+  "5": 6,
+  "[PAD]": 15,
+  "[UNK]": 14,
+  "a": 7,
+  "b": 8,
+  "c": 9,
+  "d": 10,
+  "e": 11,
+  "f": 12,
+  "g": 13,
+  "|": 0
+}