Upload processor (tokenizer + feature extractor)

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 58,
+  "<s>": 57
+}

processor_config.json

@@ -0,0 +1,12 @@
+{
+  "feature_extractor": {
+    "do_normalize": true,
+    "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+    "feature_size": 1,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "processor_class": "Wav2Vec2Processor"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "54": {
+      "content": " ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "55": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "backend": "custom",
+  "bos_token": "<s>",
+  "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 +1,59 @@
+{
+  " ": 54,
+  "[PAD]": 56,
+  "[UNK]": 55,
+  "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,
+  "ل": 23,
+  "م": 24,
+  "ن": 25,
+  "ه": 26,
+  "و": 27,
+  "ٮ": 28,
+  "ٴ": 29,
+  "ٶ": 30,
+  "ٸ": 31,
+  "ٹ": 32,
+  "ٻ": 33,
+  "پ": 34,
+  "ځ": 35,
+  "چ": 36,
+  "ڈ": 37,
+  "ڊ": 38,
+  "ڑ": 39,
+  "ژ": 40,
+  "ڙ": 41,
+  "ک": 42,
+  "ڪ": 43,
+  "ڭ": 44,
+  "گ": 45,
+  "ں": 46,
+  "ھ": 47,
+  "ہ": 48,
+  "ۂ": 49,
+  "ۃ": 50,
+  "ی": 51,
+  "ې": 52,
+  "ے": 53
+}