Upload processor

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": false,
   "sampling_rate": 16000
 }

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "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": "|"
+}

vocab.json

@@ -0,0 +1,42 @@
+{
+  "'": 18,
+  "[PAD]": 39,
+  "[UNK]": 38,
+  "a": 36,
+  "b": 29,
+  "c": 21,
+  "d": 19,
+  "e": 28,
+  "f": 30,
+  "g": 17,
+  "h": 9,
+  "i": 24,
+  "j": 13,
+  "k": 22,
+  "l": 35,
+  "m": 25,
+  "n": 3,
+  "o": 27,
+  "p": 1,
+  "q": 8,
+  "r": 12,
+  "s": 23,
+  "t": 2,
+  "u": 32,
+  "v": 33,
+  "w": 5,
+  "x": 7,
+  "y": 6,
+  "z": 26,
+  "|": 10,
+  "à": 34,
+  "â": 37,
+  "ç": 31,
+  "è": 11,
+  "é": 15,
+  "ê": 0,
+  "ô": 20,
+  "ù": 14,
+  "û": 4,
+  "œ": 16
+}