Upload processor

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 71,
+  "<s>": 70
+}

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": {
+    "68": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "71": {
+      "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 +1,72 @@
+{
+  "[PAD]": 69,
+  "[UNK]": 68,
+  "|": 0,
+  "।": 1,
+  "ଁ": 2,
+  "ଂ": 3,
+  "ଃ": 4,
+  "ଅ": 5,
+  "ଆ": 6,
+  "ଇ": 7,
+  "ଈ": 8,
+  "ଉ": 9,
+  "ଊ": 10,
+  "ଋ": 11,
+  "ଏ": 12,
+  "ଓ": 13,
+  "ଔ": 14,
+  "କ": 15,
+  "ଖ": 16,
+  "ଗ": 17,
+  "ଘ": 18,
+  "ଙ": 19,
+  "ଚ": 20,
+  "ଛ": 21,
+  "ଜ": 22,
+  "ଝ": 23,
+  "ଞ": 24,
+  "ଟ": 25,
+  "ଠ": 26,
+  "ଡ": 27,
+  "ଢ": 28,
+  "ଣ": 29,
+  "ତ": 30,
+  "ଥ": 31,
+  "ଦ": 32,
+  "ଧ": 33,
+  "ନ": 34,
+  "ପ": 35,
+  "ଫ": 36,
+  "ବ": 37,
+  "ଭ": 38,
+  "ମ": 39,
+  "ଯ": 40,
+  "ର": 41,
+  "ଲ": 42,
+  "ଳ": 43,
+  "ଵ": 44,
+  "ଶ": 45,
+  "ଷ": 46,
+  "ସ": 47,
+  "ହ": 48,
+  "଼": 49,
+  "ା": 50,
+  "ି": 51,
+  "ୀ": 52,
+  "ୁ": 53,
+  "ୂ": 54,
+  "ୃ": 55,
+  "େ": 56,
+  "ୈ": 57,
+  "ୋ": 58,
+  "ୌ": 59,
+  "୍": 60,
+  "ଡ଼": 61,
+  "ଢ଼": 62,
+  "ୟ": 63,
+  "ୱ": 64,
+  "‌": 65,
+  "–": 66,
+  "’": 67
+}