Update the AM

added_tokens.json

@@ -1 +1,4 @@
-{"<s>": 37, "</s>": 38}
+{
+  "</s>": 39,
+  "<s>": 38
+}

alphabet.json

@@ -1 +1 @@
-{"labels": [" ", "\u0430", "\u0431", "\u0432", "\u0433", "\u0434", "\u0435", "\u0436", "\u0437", "\u0438", "\u0439", "\u043a", "\u043b", "\u043c", "\u043d", "\u043e", "\u043f", "\u0440", "\u0441", "\u0442", "\u0443", "\u0444", "\u0445", "\u0446", "\u0447", "\u0448", "\u0449", "\u044c", "\u044e", "\u044f", "\u0454", "\u0456", "\u0457", "'", "-", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
+{"labels": ["'", "-", "", "\u2047", " ", "\u0430", "\u0431", "\u0432", "\u0433", "\u0434", "\u0435", "\u0436", "\u0437", "\u0438", "\u0439", "\u043a", "\u043b", "\u043c", "\u043d", "\u043e", "\u043f", "\u0440", "\u0441", "\u0442", "\u0443", "\u0444", "\u0445", "\u0446", "\u0447", "\u0448", "\u0449", "\u044c", "\u044e", "\u044f", "\u0454", "\u0456", "\u0457", "\u0491", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -77,7 +77,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 36,
+  "pad_token_id": 2,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -101,8 +101,8 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.20.0.dev0",
+  "transformers_version": "4.20.1",
   "use_weighted_layer_sum": false,
-  "vocab_size": 39,
+  "vocab_size": 40,
   "xvector_output_dim": 512
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b618404ca0a65d2e3cc80eaa58de06663ed98986395485c918ef5acc23c2bca1
-size 1262058609
+oid sha256:e39730846db353ab2c7d5fa1bcf158b42c9310443b7eeca4afc4be41864e96ee
+size 1262062705

special_tokens_map.json

@@ -1 +1,22 @@
-{"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}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{
+  "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]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,13 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "name_or_path": "Yehor/wav2vec2-xls-r-300m-uk-with-small-lm", "processor_class": "Wav2Vec2ProcessorWithLM", "special_tokens_map_file": null, "trust_remote_code": false, "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "name_or_path": "./",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,40 @@
-{"'": 33, "-": 34, "[PAD]": 36, "[UNK]": 35, "|": 0, "а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "й": 10, "к": 11, "л": 12, "м": 13, "н": 14, "о": 15, "п": 16, "р": 17, "с": 18, "т": 19, "у": 20, "ф": 21, "х": 22, "ц": 23, "ч": 24, "ш": 25, "щ": 26, "ь": 27, "ю": 28, "я": 29, "є": 30, "і": 31, "ї": 32}
+{
+  "'": 0,
+  "-": 1,
+  "[PAD]": 2,
+  "[UNK]": 3,
+  "|": 4,
+  "а": 5,
+  "б": 6,
+  "в": 7,
+  "г": 8,
+  "д": 9,
+  "е": 10,
+  "ж": 11,
+  "з": 12,
+  "и": 13,
+  "й": 14,
+  "к": 15,
+  "л": 16,
+  "м": 17,
+  "н": 18,
+  "о": 19,
+  "п": 20,
+  "р": 21,
+  "с": 22,
+  "т": 23,
+  "у": 24,
+  "ф": 25,
+  "х": 26,
+  "ц": 27,
+  "ч": 28,
+  "ш": 29,
+  "щ": 30,
+  "ь": 31,
+  "ю": 32,
+  "я": 33,
+  "є": 34,
+  "і": 35,
+  "ї": 36,
+  "ґ": 37
+}