commit files to HF hub

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+language_model/6gram_correct.arpa filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "</s>", "<s>", "\u0981", "\u0982", "\u0983", "\u0985", "\u0986", "\u0987", "\u0988", "\u0989", "\u098a", "\u098b", "\u098f", "\u0990", "\u0993", "\u0994", "\u0995", "\u0996", "\u0997", "\u0998", "\u0999", "\u099a", "\u099b", "\u099c", "\u099d", "\u099e", "\u099f", "\u09a0", "\u09a1", "\u09a2", "\u09a3", "\u09a4", "\u09a5", "\u09a6", "\u09a7", "\u09a8", "\u09aa", "\u09ab", "\u09ac", "\u09ad", "\u09ae", "\u09af", "\u09b0", "\u09b2", "\u09b6", "\u09b7", "\u09b8", "\u09b9", "\u09be", "\u09bf", "\u09c0", "\u09c1", "\u09c2", "\u09c3", "\u09c7", "\u09c8", "\u09cb", "\u09cc", "\u09cd", "\u09ce", "\u09dc", "\u09dd", "\u09df", "\u200d", "\u2047", ""], "is_bpe": false}

language_model/6gram_correct.arpa

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cbaf1ccf4c3bf75cce856debb28dd306d4c1f59d6fffc246209aff96d0bbae0
+size 49087825

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

special_tokens_map.json

@@ -1 +1,6 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -1 +1,14 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "kabir5297/BanglaASR-XLSR-SmallLM",
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -1 +1,69 @@
-{"</s>": 1, "<s>": 2, "ঁ": 3, "ং": 4, "ঃ": 5, "অ": 6, "আ": 7, "ই": 8, "ঈ": 9, "উ": 10, "ঊ": 11, "ঋ": 12, "এ": 13, "ঐ": 14, "ও": 15, "ঔ": 16, "ক": 17, "খ": 18, "গ": 19, "ঘ": 20, "ঙ": 21, "চ": 22, "ছ": 23, "জ": 24, "ঝ": 25, "ঞ": 26, "ট": 27, "ঠ": 28, "ড": 29, "ঢ": 30, "ণ": 31, "ত": 32, "থ": 33, "দ": 34, "ধ": 35, "ন": 36, "প": 37, "ফ": 38, "ব": 39, "ভ": 40, "ম": 41, "য": 42, "র": 43, "ল": 44, "শ": 45, "ষ": 46, "স": 47, "হ": 48, "া": 49, "ি": 50, "ী": 51, "ু": 52, "ূ": 53, "ৃ": 54, "ে": 55, "ৈ": 56, "ো": 57, "ৌ": 58, "্": 59, "ৎ": 60, "ড়": 61, "ঢ়": 62, "য়": 63, "‍": 64, "|": 0, "[UNK]": 65, "[PAD]": 66}
+{
+  "</s>": 1,
+  "<s>": 2,
+  "[PAD]": 66,
+  "[UNK]": 65,
+  "|": 0,
+  "ঁ": 3,
+  "ং": 4,
+  "ঃ": 5,
+  "অ": 6,
+  "আ": 7,
+  "ই": 8,
+  "ঈ": 9,
+  "উ": 10,
+  "ঊ": 11,
+  "ঋ": 12,
+  "এ": 13,
+  "ঐ": 14,
+  "ও": 15,
+  "ঔ": 16,
+  "ক": 17,
+  "খ": 18,
+  "গ": 19,
+  "ঘ": 20,
+  "ঙ": 21,
+  "চ": 22,
+  "ছ": 23,
+  "জ": 24,
+  "ঝ": 25,
+  "ঞ": 26,
+  "ট": 27,
+  "ঠ": 28,
+  "ড": 29,
+  "ঢ": 30,
+  "ণ": 31,
+  "ত": 32,
+  "থ": 33,
+  "দ": 34,
+  "ধ": 35,
+  "ন": 36,
+  "প": 37,
+  "ফ": 38,
+  "ব": 39,
+  "ভ": 40,
+  "ম": 41,
+  "য": 42,
+  "র": 43,
+  "ল": 44,
+  "শ": 45,
+  "ষ": 46,
+  "স": 47,
+  "হ": 48,
+  "া": 49,
+  "ি": 50,
+  "ী": 51,
+  "ু": 52,
+  "ূ": 53,
+  "ৃ": 54,
+  "ে": 55,
+  "ৈ": 56,
+  "ো": 57,
+  "ৌ": 58,
+  "্": 59,
+  "ৎ": 60,
+  "ড়": 61,
+  "ঢ়": 62,
+  "য়": 63,
+  "‍": 64
+}