Upload processor (tokenizer + feature extractor)

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 61,
+  "<s>": 60
+}

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

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "58": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "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

@@ -0,0 +1,62 @@
+{
+  " ": 57,
+  "[PAD]": 59,
+  "[UNK]": 58,
+  "ء": 0,
+  "ا": 1,
+  "ب": 2,
+  "ت": 3,
+  "ث": 4,
+  "ج": 5,
+  "ح": 6,
+  "خ": 7,
+  "د": 8,
+  "ذ": 9,
+  "ر": 10,
+  "ز": 11,
+  "س": 12,
+  "ش": 13,
+  "ص": 14,
+  "ض": 15,
+  "ط": 16,
+  "ظ": 17,
+  "ع": 18,
+  "غ": 19,
+  "ـ": 20,
+  "ف": 21,
+  "ق": 22,
+  "ك": 23,
+  "ل": 24,
+  "م": 25,
+  "ن": 26,
+  "ه": 27,
+  "و": 28,
+  "ي": 29,
+  "ٮ": 30,
+  "ٱ": 31,
+  "ٴ": 32,
+  "ٶ": 33,
+  "ٸ": 34,
+  "ٹ": 35,
+  "ٻ": 36,
+  "پ": 37,
+  "ځ": 38,
+  "چ": 39,
+  "ڈ": 40,
+  "ڊ": 41,
+  "ڑ": 42,
+  "ژ": 43,
+  "ڙ": 44,
+  "ک": 45,
+  "ڪ": 46,
+  "ڭ": 47,
+  "گ": 48,
+  "ں": 49,
+  "ھ": 50,
+  "ہ": 51,
+  "ۂ": 52,
+  "ۃ": 53,
+  "ی": 54,
+  "ې": 55,
+  "ے": 56
+}