Adding odia model

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", "\u0b08", "\u0b1c", "\u0b5f", "\u0b15", "\u0b18", "\u0b3c", "\u0b30", "\u0b26", "\u0b4d", "\u0b47", "\u0b41", "\u0b03", ".", "\u0b4b", "\u0b71", "\u0b05", "\u0b14", "\u0b0a", "\u0b0f", "\u0b32", "\u0b2a", "\u0b1f", "\u0b02", "\u0b35", "\u0b48", "\u0b27", "\u0b24", "\u0b33", "\u0b37", "\u0b3f", "\u0b3e", "\u0b2e", "\u0b23", "\u0b28", " ", "\u0b01", "\u0b19", "\u0b5d", "\u0b16", "\u0b20", "\u0b22", "\u0b43", "\u0b4c", "\u0b2b", "\u0b1b", "\u0b17", "\u0b1d", "\u0b5c", "\u0b2f", "\u0b38", "\u0b1e", "\u0b21", "\u0b0b", "\u0b2c", "\u0b13", "\u0b40", "\u0b09", "\u0b07", "\u0b2d", "\u0b42", "\u0b1a", "\u0b36", "\u0b39", "\u0b25", "\u0b06"], "is_bpe": false}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-960h-lv60-self",
+  "activation_dropout": 0.1,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 69,
+  "xvector_output_dim": 512
+}

language_model/.gitattributes

@@ -0,0 +1,2 @@
+unigrams.txt filter=lfs diff=lfs merge=lfs -text
+lm.binary filter=lfs diff=lfs merge=lfs -text

language_model/attrs.json

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

language_model/lm.binary

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1463f4876ed8b96b368645e0f4367fbf91dfe1ee54d9674dbd062ca18572929a
+size 388294109

language_model/unigrams.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09ab94328dc70b7eb4055370e6dd2c86e5c945c523d9618fed6f0938cfea5e31
+size 12043782

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 sha256:422eac4eb5a418e9c1da84e9b0dd1834d162664c716c96232a568a20d9b7d97c
+size 1262200689

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}

vocab.json

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