Upload 9 files

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *_000.txt filter=lfs diff=lfs merge=lfs -text
 *.binary filter=lfs diff=lfs merge=lfs -text
+unigrams_500000.txt filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-960h-lv60-self",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 69,
+  "xvector_output_dim": 512
+}

dict.ltr.txt

@@ -0,0 +1,65 @@
+ଈ 0
+ଜ 1
+ୟ 2
+କ 3
+ଘ 4
+଼ 5
+ର 6
+ଦ 7
+୍ 8
+େ 9
+ୁ 10
+ଃ 11
+. 12
+ୋ 13
+ୱ 14
+ଅ 15
+ଔ 16
+ଊ 17
+ଏ 18
+ଲ 19
+ପ 20
+ଟ 21
+ଂ 22
+ଵ 23
+ୈ 24
+ଧ 25
+ତ 26
+ଳ 27
+ଷ 28
+ି 29
+ା 30
+ମ 31
+ଣ 32
+ନ 33
+| 34
+ଁ 35
+ଙ 36
+ଢ଼ 37
+ଖ 38
+ଠ 39
+ଢ 40
+ୃ 41
+ୌ 42
+ଫ 43
+ଛ 44
+ଗ 45
+ଝ 46
+ଡ଼ 47
+ଯ 48
+ସ 49
+ଞ 50
+ଡ 51
+ଋ 52
+ବ 53
+ଓ 54
+ୀ 55
+ଉ 56
+ଇ 57
+ଭ 58
+ୂ 59
+ଚ 60
+ଶ 61
+ହ 62
+ଥ 63
+ଆ 64

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ecdecd56c322ebad7199f8a9683e40e6ac5558f1e708dc71b472991c816ce6
+size 1262178861

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>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

topk-500000_lm.binary

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab98755be4d001d670838216ef76df4478db1da4a3e8b1fa4ff9fa1c8ff3882e
+size 614416741

unigrams_500000.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d012b35336276bdae392717e251663bc6aa3d03f05eaa69899ee1559a40280
+size 12928063

vocab.json

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