Update processor: 2026-03-23T11:32:54.920296

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "41": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,54 @@
+{
+  "\n": 45,
+  "</s>": 44,
+  "<s>": 43,
+  "[PAD]": 42,
+  "[UNK]": 41,
+  "a": 3,
+  "b": 4,
+  "c": 28,
+  "d": 27,
+  "e": 5,
+  "f": 33,
+  "g": 7,
+  "h": 32,
+  "i": 6,
+  "j": 16,
+  "k": 29,
+  "l": 25,
+  "m": 15,
+  "n": 19,
+  "o": 24,
+  "p": 17,
+  "q": 14,
+  "r": 2,
+  "s": 23,
+  "t": 8,
+  "u": 22,
+  "v": 0,
+  "w": 36,
+  "x": 13,
+  "y": 10,
+  "z": 30,
+  "|": 18,
+  "ç": 20,
+  "ê": 11,
+  "î": 31,
+  "û": 26,
+  "đ": 12,
+  "ġ": 39,
+  "ħ": 1,
+  "ŋ": 35,
+  "ř": 37,
+  "ş": 34,
+  "ɫ": 21,
+  "ʕ": 38,
+  "̀": 46,
+  "̣": 40,
+  "ḥ": 9,
+  "ṣ": 47,
+  "‘": 48,
+  "’": 49,
+  "…": 50,
+  "꞊": 51
+}