Upload processor

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 70,
+  "<s>": 69
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

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 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "67": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,71 @@
+{
+  "[PAD]": 68,
+  "[UNK]": 67,
+  "|": 0,
+  "ಂ": 1,
+  "ಃ": 2,
+  "ಅ": 3,
+  "ಆ": 4,
+  "ಇ": 5,
+  "ಈ": 6,
+  "ಉ": 7,
+  "ಊ": 8,
+  "ಋ": 9,
+  "ಎ": 10,
+  "ಏ": 11,
+  "ಐ": 12,
+  "ಒ": 13,
+  "ಓ": 14,
+  "ಔ": 15,
+  "ಕ": 16,
+  "ಖ": 17,
+  "ಗ": 18,
+  "ಘ": 19,
+  "ಚ": 20,
+  "ಛ": 21,
+  "ಜ": 22,
+  "ಝ": 23,
+  "ಞ": 24,
+  "ಟ": 25,
+  "ಠ": 26,
+  "ಡ": 27,
+  "ಢ": 28,
+  "ಣ": 29,
+  "ತ": 30,
+  "ಥ": 31,
+  "ದ": 32,
+  "ಧ": 33,
+  "ನ": 34,
+  "ಪ": 35,
+  "ಫ": 36,
+  "ಬ": 37,
+  "ಭ": 38,
+  "ಮ": 39,
+  "ಯ": 40,
+  "ರ": 41,
+  "ಲ": 42,
+  "ಳ": 43,
+  "ವ": 44,
+  "ಶ": 45,
+  "ಷ": 46,
+  "ಸ": 47,
+  "ಹ": 48,
+  "ಾ": 49,
+  "ಿ": 50,
+  "ೀ": 51,
+  "ು": 52,
+  "ೂ": 53,
+  "ೃ": 54,
+  "ೆ": 55,
+  "ೇ": 56,
+  "ೈ": 57,
+  "ೊ": 58,
+  "ೋ": 59,
+  "ೌ": 60,
+  "್": 61,
+  "ೕ": 62,
+  "ೖ": 63,
+  "​": 64,
+  "‌": 65,
+  "‍": 66
+}