Initial commit of Hindi Wav2Vec Model

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": 63,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 64
+}

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 sha256:7af3f44f6dd07c76ab6533cb2bbb4ae62d4c87cc2583f2a82c150c9e7bf4936d
+size 1262196247

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": "|"}

vocab.json

@@ -0,0 +1 @@
+{"न": 0, "च": 1, "थ": 2, "ी": 3, "ऐ": 4, "ृ": 5, "ध": 6, "य": 7, "ह": 8, "ऊ": 9, "म": 10, "ण": 11, "ै": 13, "ौ": 14, "ा": 15, "ल": 16, "त": 17, "इ": 18, "ढ़": 19, "ष": 20, "भ": 21, "ग़": 22, "ख": 23, "ड़": 24, "ए": 25, "व": 26, "ु": 27, "ओ": 28, "र": 29, "श": 30, "औ": 31, "ट": 32, "आ": 33, "ो": 34, "ढ": 35, "झ": 36, "ग": 37, "ज़": 38, "अ": 39, "े": 40, "प": 41, "घ": 42, "द": 43, "ई": 44, "फ़": 45, "ब": 46, "ड": 47, "ँ": 48, "छ": 49, "ू": 50, "फ": 51, "ि": 52, "स": 53, "्": 54, "क": 55, "उ": 56, "ठ": 57, "ं": 58, "़": 59, "ज": 60, "क़": 61, "|": 12, "[UNK]": 62, "[PAD]": 63}