add LM

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "⁇", " ", "-", "ё", "а", "б", "в", "г", "д", "е", "ж", "з", "и", "й", "к", "л", "м", "н", "о", "п", "р", "с", "т", "у", "ф", "х", "ц", "ч", "ш", "щ", "ъ", "ы", "ь", "э", "ю", "я"], "is_bpe": false}

config.json

@@ -48,7 +48,6 @@
   "feat_proj_dropout": 0.05,
   "feat_quantizer_dropout": 0.0,
   "final_dropout": 0.0,
-  "gradient_checkpointing": true,
   "hidden_act": "gelu",
   "hidden_dropout": 0.05,
   "hidden_size": 1024,

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/lm.binary

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a8fba99ad0d5157e060ea7bee83adb7bc7025606e6f98a783da1413b6edbaf
+size 1486935543

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c72ae916afa54951fe3bd6094c95e2895c1c7881a20e02ef640aa27cdb4874
+size 32849086

preprocessor_config.json

@@ -5,5 +5,6 @@
   "padding_side": "right",
   "padding_value": 0.0,
   "return_attention_mask": true,
-  "sampling_rate": 16000
+  "sampling_rate": 16000,
+  "processor_class": "Wav2Vec2ProcessorWithLM"
 }

vocab.json

@@ -1 +1 @@
-{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "-": 5, "Ё": 6, "А": 7, "Б": 8, "В": 9, "Г": 10, "Д": 11, "Е": 12, "Ж": 13, "З": 14, "И": 15, "Й": 16, "К": 17, "Л": 18, "М": 19, "Н": 20, "О": 21, "П": 22, "Р": 23, "С": 24, "Т": 25, "У": 26, "Ф": 27, "Х": 28, "Ц": 29, "Ч": 30, "Ш": 31, "Щ": 32, "Ъ": 33, "Ы": 34, "Ь": 35, "Э": 36, "Ю": 37, "Я": 38}
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "-": 5, "ё": 6, "а": 7, "б": 8, "в": 9, "г": 10, "д": 11, "е": 12, "ж": 13, "з": 14, "и": 15, "й": 16, "к": 17, "л": 18, "м": 19, "н": 20, "о": 21, "п": 22, "р": 23, "с": 24, "т": 25, "у": 26, "ф": 27, "х": 28, "ц": 29, "ч": 30, "ш": 31, "щ": 32, "ъ": 33, "ы": 34, "ь": 35, "э": 36, "ю": 37, "я": 38}