Upload processor

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 74,
+  "<s>": 73
+}

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 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "71": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "74": {
+      "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 +1,75 @@
+{
+  "[PAD]": 72,
+  "[UNK]": 71,
+  "|": 0,
+  "ក": 1,
+  "ខ": 2,
+  "គ": 3,
+  "ឃ": 4,
+  "ង": 5,
+  "ច": 6,
+  "ឆ": 7,
+  "ជ": 8,
+  "ឈ": 9,
+  "ញ": 10,
+  "ដ": 11,
+  "ឋ": 12,
+  "ឌ": 13,
+  "ឍ": 14,
+  "ណ": 15,
+  "ត": 16,
+  "ថ": 17,
+  "ទ": 18,
+  "ធ": 19,
+  "ន": 20,
+  "ប": 21,
+  "ផ": 22,
+  "ព": 23,
+  "ភ": 24,
+  "ម": 25,
+  "យ": 26,
+  "រ": 27,
+  "ល": 28,
+  "វ": 29,
+  "ស": 30,
+  "ហ": 31,
+  "ឡ": 32,
+  "អ": 33,
+  "ឥ": 34,
+  "ឧ": 35,
+  "ឪ": 36,
+  "ឫ": 37,
+  "ឬ": 38,
+  "ឭ": 39,
+  "ឮ": 40,
+  "ឯ": 41,
+  "ឱ": 42,
+  "ា": 43,
+  "ិ": 44,
+  "ី": 45,
+  "ឹ": 46,
+  "ឺ": 47,
+  "ុ": 48,
+  "ូ": 49,
+  "ួ": 50,
+  "ើ": 51,
+  "ឿ": 52,
+  "ៀ": 53,
+  "េ": 54,
+  "ែ": 55,
+  "ៃ": 56,
+  "ោ": 57,
+  "ៅ": 58,
+  "ំ": 59,
+  "ះ": 60,
+  "ៈ": 61,
+  "៉": 62,
+  "៊": 63,
+  "់": 64,
+  "៌": 65,
+  "៍": 66,
+  "៎": 67,
+  "៏": 68,
+  "័": 69,
+  "្": 70
+}