Upload processor

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 66,
+  "<s>": 65
+}

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": {
+    "63": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "66": {
+      "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 +1,67 @@
+{
+  "[PAD]": 64,
+  "[UNK]": 63,
+  "|": 0,
+  "ఁ": 1,
+  "ం": 2,
+  "ః": 3,
+  "అ": 4,
+  "ఆ": 5,
+  "ఇ": 6,
+  "ఈ": 7,
+  "ఉ": 8,
+  "ఊ": 9,
+  "ఋ": 10,
+  "ఎ": 11,
+  "ఏ": 12,
+  "ఐ": 13,
+  "ఒ": 14,
+  "ఓ": 15,
+  "ఔ": 16,
+  "క": 17,
+  "ఖ": 18,
+  "గ": 19,
+  "ఘ": 20,
+  "ఙ": 21,
+  "చ": 22,
+  "ఛ": 23,
+  "జ": 24,
+  "ఞ": 25,
+  "ట": 26,
+  "ఠ": 27,
+  "డ": 28,
+  "ఢ": 29,
+  "ణ": 30,
+  "త": 31,
+  "థ": 32,
+  "ద": 33,
+  "ధ": 34,
+  "న": 35,
+  "ప": 36,
+  "ఫ": 37,
+  "బ": 38,
+  "భ": 39,
+  "మ": 40,
+  "య": 41,
+  "ర": 42,
+  "ల": 43,
+  "ళ": 44,
+  "వ": 45,
+  "శ": 46,
+  "ష": 47,
+  "స": 48,
+  "హ": 49,
+  "ా": 50,
+  "ి": 51,
+  "ీ": 52,
+  "ు": 53,
+  "ూ": 54,
+  "ృ": 55,
+  "ె": 56,
+  "ే": 57,
+  "ై": 58,
+  "ొ": 59,
+  "ో": 60,
+  "ౌ": 61,
+  "్": 62
+}