Adding Tamil Model

config.json

@@ -0,0 +1,81 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token": "<s>",
+  "bos_token_id": 0,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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_lower_case": false,
+  "do_stable_layer_norm": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "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_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "pad_token": "[PAD]",
+  "pad_token_id": 1,
+  "proj_codevector_dim": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "unk_token": "[UNK]",
+  "vocab_size": 53,
+  "word_delimiter_token": "|"
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00adef7dc21c04f9014807f73c21c5fa12f9284aed6a5494a72bfc42ff3e55e7
+size 377731607

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"}

vocab.json

@@ -0,0 +1 @@
+{"<s>": 0, "<pad>": 1, "</s>": 2, "<unk>": 3, "|": 4, "ஃ": 5, "அ": 6, "ஆ": 7, "இ": 8, "ஈ": 9, "உ": 10, "ஊ": 11, "எ": 12, "ஏ": 13, "ஐ": 14, "ஒ": 15, "ஓ": 16, "ஔ": 17, "க": 18, "ங": 19, "ச": 20, "ஜ": 21, "ஞ": 22, "ட": 23, "ண": 24, "த": 25, "ந": 26, "ன": 27, "ப": 28, "ம": 29, "ய": 30, "ர": 31, "ற": 32, "ல": 33, "ள": 34, "ழ": 35, "வ": 36, "ஶ": 37, "ஷ": 38, "ஸ": 39, "ஹ": 40, "ா": 41, "ி": 42, "ீ": 43, "ு": 44, "ூ": 45, "ெ": 46, "ே": 47, "ை": 48, "ொ": 49, "ோ": 50, "ௌ": 51, "்": 52}