Upload processor

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

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 +1,14 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "ai4bharat/indicwav2vec_v1_gujarati",
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": "/home/users/jatin/.cache/huggingface/hub/models--ai4bharat--indicwav2vec_v1_gujarati/snapshots/ce9630d2f0aa34940983515b28787d918470d130/special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,72 @@
+{
+  ",": 9,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "|": 4,
+  "ઁ": 46,
+  "ં": 18,
+  "ઃ": 30,
+  "અ": 24,
+  "આ": 34,
+  "ઇ": 40,
+  "ઈ": 32,
+  "ઉ": 48,
+  "ઊ": 62,
+  "ઋ": 10,
+  "ઍ": 67,
+  "એ": 68,
+  "ઐ": 41,
+  "ઑ": 54,
+  "ઓ": 6,
+  "ઔ": 63,
+  "ક": 11,
+  "ખ": 69,
+  "ગ": 58,
+  "ઘ": 56,
+  "ઙ": 37,
+  "ચ": 27,
+  "છ": 43,
+  "જ": 28,
+  "ઝ": 52,
+  "ઞ": 25,
+  "ટ": 59,
+  "ઠ": 31,
+  "ડ": 33,
+  "ઢ": 42,
+  "ણ": 22,
+  "ત": 14,
+  "થ": 38,
+  "દ": 47,
+  "ધ": 64,
+  "ન": 5,
+  "પ": 60,
+  "ફ": 61,
+  "બ": 7,
+  "ભ": 39,
+  "મ": 15,
+  "ય": 17,
+  "ર": 19,
+  "લ": 65,
+  "ળ": 21,
+  "વ": 49,
+  "શ": 20,
+  "ષ": 36,
+  "સ": 13,
+  "હ": 23,
+  "ા": 45,
+  "િ": 44,
+  "ી": 12,
+  "ુ": 35,
+  "ૂ": 53,
+  "ૃ": 16,
+  "ૄ": 57,
+  "ૅ": 29,
+  "ે": 55,
+  "ૈ": 26,
+  "ૉ": 51,
+  "ો": 8,
+  "ૌ": 66,
+  "્": 50
+}