Odia model intial commit

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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": "mean",
+  "ctc_zero_infinity": false,
+  "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": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 66,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 67
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07312c337901d5688a393efc094561c64855472576baa66d55f5820069e0c1f7
+size 1262208535

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": "|", "special_tokens_map_file": "/content/drive/MyDrive/ASR_models/wav2vec2-large-xlsr-odia/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/content/drive/MyDrive/ASR_models/wav2vec2-large-xlsr-odia"}

vocab.json

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