Upload processor

added_tokens.json

@@ -1,4 +1,4 @@
-{
-  "</s>": 69,
-  "<s>": 68
-}
+{
+  "</s>": 66,
+  "<s>": 65
+}

preprocessor_config.json

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

special_tokens_map.json

@@ -1,6 +1,6 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
-}
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1,160 +1,153 @@
-{
-  "added_tokens_decoder": {
-    "0": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "1": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "3": {
-      "content": "aɪ",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "4": {
-      "content": "aʊ",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "5": {
-      "content": "aː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "8": {
-      "content": "dʒ",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "10": {
-      "content": "eː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "14": {
-      "content": "iː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "21": {
-      "content": "oː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "23": {
-      "content": "pf",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "27": {
-      "content": "ts",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "28": {
-      "content": "tʃ",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "29": {
-      "content": "uː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "33": {
-      "content": "yː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "39": {
-      "content": "øː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "49": {
-      "content": "ɛː",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "68": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "69": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "do_lower_case": false,
-  "eos_token": "</s>",
-  "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": "|"
-}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "aɪ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "4": {
+      "content": "aʊ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "dʒ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "eː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "iː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "oː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "pf",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "ts",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "tʃ",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "uː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "yː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "øː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "ɛː",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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

@@ -1,70 +1,67 @@
-{
-  "[PAD]": 0,
-  "[UNK]": 1,
-  "a": 2,
-  "aɪ": 3,
-  "aʊ": 4,
-  "aː": 5,
-  "b": 6,
-  "d": 7,
-  "dʒ": 8,
-  "e": 9,
-  "eː": 10,
-  "f": 11,
-  "h": 12,
-  "i": 13,
-  "iː": 14,
-  "j": 15,
-  "k": 16,
-  "l": 17,
-  "m": 18,
-  "n": 19,
-  "o": 20,
-  "oː": 21,
-  "p": 22,
-  "pf": 23,
-  "r": 24,
-  "s": 25,
-  "t": 26,
-  "ts": 27,
-  "tʃ": 28,
-  "uː": 29,
-  "v": 30,
-  "w": 31,
-  "x": 32,
-  "yː": 33,
-  "z": 34,
-  "|": 35,
-  "ç": 36,
-  "ð": 37,
-  "ø": 38,
-  "øː": 39,
-  "ŋ": 40,
-  "œ": 41,
-  "ɐ": 42,
-  "ɑ": 43,
-  "ɒ": 44,
-  "ɔ": 45,
-  "ɕ": 46,
-  "ə": 47,
-  "ɛ": 48,
-  "ɛː": 49,
-  "ɜ": 50,
-  "ɡ": 51,
-  "ɪ": 52,
-  "ɲ": 53,
-  "ɹ": 54,
-  "ɾ": 55,
-  "ʃ": 56,
-  "ʊ": 57,
-  "ʌ": 58,
-  "ʏ": 59,
-  "ʒ": 60,
-  "ʲ": 61,
-  "ˈ": 62,
-  "ˌ": 63,
-  "ː": 64,
-  "̃": 65,
-  "̩": 66,
-  "θ": 67
-}
+{
+  "[PAD]": 0,
+  "[UNK]": 1,
+  "a": 2,
+  "aɪ": 3,
+  "aʊ": 4,
+  "b": 5,
+  "d": 6,
+  "dʒ": 7,
+  "e": 8,
+  "eː": 9,
+  "f": 10,
+  "h": 11,
+  "i": 12,
+  "iː": 13,
+  "j": 14,
+  "k": 15,
+  "l": 16,
+  "m": 17,
+  "n": 18,
+  "oː": 19,
+  "p": 20,
+  "pf": 21,
+  "r": 22,
+  "s": 23,
+  "t": 24,
+  "ts": 25,
+  "tʃ": 26,
+  "uː": 27,
+  "v": 28,
+  "w": 29,
+  "x": 30,
+  "y": 31,
+  "yː": 32,
+  "z": 33,
+  "|": 34,
+  "ç": 35,
+  "ð": 36,
+  "ø": 37,
+  "øː": 38,
+  "ŋ": 39,
+  "œ": 40,
+  "ɐ": 41,
+  "ɑ": 42,
+  "ɒ": 43,
+  "ɔ": 44,
+  "ɕ": 45,
+  "ə": 46,
+  "ɛ": 47,
+  "ɛː": 48,
+  "ɜ": 49,
+  "ɡ": 50,
+  "ɪ": 51,
+  "ɲ": 52,
+  "ɹ": 53,
+  "ɾ": 54,
+  "ʃ": 55,
+  "ʊ": 56,
+  "ʌ": 57,
+  "ʒ": 58,
+  "ʲ": 59,
+  "ˈ": 60,
+  "ˌ": 61,
+  "ː": 62,
+  "̃": 63,
+  "θ": 64
+}