Added model and processor for 90 accuracy wav2vec

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "anish-shilpakar/wav2vec2-nepali-asr-v1",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.12,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "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": "mean",
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.12,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 62,
+  "proj_codevector_dim": 768,
+  "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": "4.26.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 63,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "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 sha256:1d73a1d046e58969ff6805fa5a53dc7f9e74262e903937f59d7545e04672dbc0
+size 1262160173

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 +1,12 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73892696d45cf8565329284ac8566d935d43f87b8841ec2f385e742000f006f
+size 3451

vocab.json

@@ -0,0 +1,65 @@
+{
+  "[PAD]": 62,
+  "[UNK]": 61,
+  "|": 43,
+  "ँ": 46,
+  "ं": 54,
+  "ः": 37,
+  "अ": 40,
+  "आ": 51,
+  "इ": 30,
+  "ई": 0,
+  "उ": 42,
+  "ऊ": 24,
+  "ऋ": 55,
+  "ए": 14,
+  "ऐ": 45,
+  "ओ": 31,
+  "औ": 2,
+  "क": 12,
+  "ख": 4,
+  "ग": 58,
+  "घ": 39,
+  "ङ": 25,
+  "च": 60,
+  "छ": 19,
+  "ज": 48,
+  "झ": 1,
+  "ञ": 15,
+  "ट": 11,
+  "ठ": 22,
+  "ड": 50,
+  "ढ": 8,
+  "ण": 57,
+  "त": 33,
+  "थ": 13,
+  "द": 6,
+  "ध": 7,
+  "न": 27,
+  "प": 20,
+  "फ": 17,
+  "ब": 28,
+  "भ": 21,
+  "म": 59,
+  "य": 23,
+  "र": 16,
+  "ल": 3,
+  "व": 32,
+  "श": 38,
+  "ष": 34,
+  "स": 41,
+  "ह": 49,
+  "ा": 26,
+  "ि": 35,
+  "ी": 36,
+  "ु": 18,
+  "ू": 52,
+  "ृ": 56,
+  "े": 44,
+  "ै": 9,
+  "ो": 10,
+  "ौ": 29,
+  "्": 47,
+  "।": 53,
+  "‍": 5
+}