fix: update and move processor files

preprocessor_config.json

@@ -5,6 +5,6 @@
   "padding_side": "right",
   "padding_value": 0.0,
   "processor_class": "Wav2Vec2Processor",
-  "return_attention_mask": false,
+  "return_attention_mask": true,
   "sampling_rate": 16000
 }

processor/added_tokens.json

@@ -1,4 +0,0 @@
-{
-  "</s>": 42,
-  "[PAD]": 41
-}

processor/preprocessor_config.json

@@ -1,10 +0,0 @@
-{
-  "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
-}

processor/special_tokens_map.json

@@ -1,6 +0,0 @@
-{
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "[UNK]"
-}

processor/tokenizer_config.json

@@ -1,41 +0,0 @@
-{
-  "added_tokens_decoder": {
-    "40": {
-      "content": "[UNK]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "41": {
-      "content": "[PAD]",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": true,
-      "single_word": false,
-      "special": false
-    },
-    "42": {
-      "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": "|"
-}

processor/vocab.json

@@ -1,43 +0,0 @@
-{
-  "'": 30,
-  "0": 8,
-  "1": 7,
-  "2": 21,
-  "3": 25,
-  "4": 26,
-  "5": 34,
-  "6": 6,
-  "7": 36,
-  "8": 3,
-  "9": 15,
-  "[PAD]": 41,
-  "[UNK]": 40,
-  "a": 18,
-  "b": 4,
-  "c": 11,
-  "d": 29,
-  "e": 14,
-  "f": 5,
-  "g": 12,
-  "h": 22,
-  "i": 17,
-  "j": 31,
-  "k": 35,
-  "l": 37,
-  "m": 19,
-  "n": 32,
-  "o": 23,
-  "p": 9,
-  "q": 10,
-  "r": 38,
-  "s": 28,
-  "t": 13,
-  "u": 24,
-  "v": 0,
-  "w": 27,
-  "x": 20,
-  "y": 16,
-  "z": 33,
-  "|": 1,
-  "ñ": 2
-}

special_tokens_map.json

@@ -1,24 +1,6 @@
 {
   "bos_token": "<s>",
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "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
-  }
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
 }

vocab.json

@@ -1,43 +1,43 @@
 {
-  "'": 34,
-  "0": 25,
+  "'": 30,
+  "0": 8,
   "1": 7,
-  "2": 12,
-  "3": 3,
-  "4": 10,
-  "5": 1,
-  "6": 18,
-  "7": 31,
-  "8": 13,
-  "9": 28,
+  "2": 21,
+  "3": 25,
+  "4": 26,
+  "5": 34,
+  "6": 6,
+  "7": 36,
+  "8": 3,
+  "9": 15,
   "[PAD]": 41,
   "[UNK]": 40,
-  "a": 24,
-  "b": 9,
-  "c": 6,
-  "d": 19,
-  "e": 30,
-  "f": 22,
-  "g": 36,
-  "h": 27,
-  "i": 32,
-  "j": 37,
-  "k": 21,
-  "l": 2,
-  "m": 20,
-  "n": 11,
-  "o": 38,
-  "p": 4,
-  "q": 15,
-  "r": 35,
-  "s": 23,
-  "t": 0,
-  "u": 14,
-  "v": 33,
-  "w": 16,
-  "x": 17,
-  "y": 26,
-  "z": 29,
-  "|": 8,
-  "ñ": 5
+  "a": 18,
+  "b": 4,
+  "c": 11,
+  "d": 29,
+  "e": 14,
+  "f": 5,
+  "g": 12,
+  "h": 22,
+  "i": 17,
+  "j": 31,
+  "k": 35,
+  "l": 37,
+  "m": 19,
+  "n": 32,
+  "o": 23,
+  "p": 9,
+  "q": 10,
+  "r": 38,
+  "s": 28,
+  "t": 13,
+  "u": 24,
+  "v": 0,
+  "w": 27,
+  "x": 20,
+  "y": 16,
+  "z": 33,
+  "|": 1,
+  "ñ": 2
 }