Upload lm-boosted decoder

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/5gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05194189f36984f894a2012c12ce609837b760fca6d56e3bf2a513122004c21
+size 4603300

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.

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

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "ai-light-dance_singing_ft_wav2vec2-large-lv60", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "gary109/ai-light-dance_singing_ft_wav2vec2-large-lv60", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}