harveenchadha commited on
Commit
c24b594
1 Parent(s): cd1a296

Adding Tamil Model

Browse files
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForCTC"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token": "<s>",
9
+ "bos_token_id": 0,
10
+ "codevector_dim": 256,
11
+ "contrastive_logits_temperature": 0.1,
12
+ "conv_bias": false,
13
+ "conv_dim": [
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "conv_kernel": [
23
+ 10,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2
30
+ ],
31
+ "conv_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "sum",
41
+ "ctc_zero_infinity": false,
42
+ "diversity_loss_weight": 0.1,
43
+ "do_lower_case": false,
44
+ "do_stable_layer_norm": false,
45
+ "eos_token": "</s>",
46
+ "eos_token_id": 2,
47
+ "feat_extract_activation": "gelu",
48
+ "feat_extract_norm": "group",
49
+ "feat_proj_dropout": 0.1,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.1,
52
+ "gradient_checkpointing": false,
53
+ "hidden_act": "gelu",
54
+ "hidden_dropout": 0.1,
55
+ "hidden_size": 768,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 3072,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.1,
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_prob": 0.05,
64
+ "model_type": "wav2vec2",
65
+ "num_attention_heads": 12,
66
+ "num_codevector_groups": 2,
67
+ "num_codevectors_per_group": 320,
68
+ "num_conv_pos_embedding_groups": 16,
69
+ "num_conv_pos_embeddings": 128,
70
+ "num_feat_extract_layers": 7,
71
+ "num_hidden_layers": 12,
72
+ "num_negatives": 100,
73
+ "pad_token": "[PAD]",
74
+ "pad_token_id": 1,
75
+ "proj_codevector_dim": 256,
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.9.1",
78
+ "unk_token": "[UNK]",
79
+ "vocab_size": 53,
80
+ "word_delimiter_token": "|"
81
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00adef7dc21c04f9014807f73c21c5fa12f9284aed6a5494a72bfc42ff3e55e7
3
+ size 377731607
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +1 @@
 
 
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}