KalyanRamM
commited on
Commit
•
300b5b9
1
Parent(s):
080e38d
Training in progress, step 600
Browse files
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 72,
|
3 |
+
"<s>": 71
|
4 |
}
|
config.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"adapter_act": "relu",
|
5 |
+
"adapter_kernel_size": 3,
|
6 |
+
"adapter_stride": 2,
|
7 |
+
"add_adapter": true,
|
8 |
+
"apply_spec_augment": false,
|
9 |
+
"architectures": [
|
10 |
+
"Wav2Vec2BertForCTC"
|
11 |
+
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
+
"bos_token_id": 1,
|
14 |
+
"classifier_proj_size": 768,
|
15 |
+
"codevector_dim": 768,
|
16 |
+
"conformer_conv_dropout": 0.1,
|
17 |
+
"contrastive_logits_temperature": 0.1,
|
18 |
+
"conv_depthwise_kernel_size": 31,
|
19 |
+
"ctc_loss_reduction": "mean",
|
20 |
+
"ctc_zero_infinity": false,
|
21 |
+
"diversity_loss_weight": 0.1,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"feat_proj_dropout": 0.0,
|
24 |
+
"feat_quantizer_dropout": 0.0,
|
25 |
+
"feature_projection_input_dim": 160,
|
26 |
+
"final_dropout": 0.1,
|
27 |
+
"hidden_act": "swish",
|
28 |
+
"hidden_dropout": 0.0,
|
29 |
+
"hidden_size": 1024,
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 4096,
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"layerdrop": 0.0,
|
34 |
+
"left_max_position_embeddings": 64,
|
35 |
+
"mask_feature_length": 10,
|
36 |
+
"mask_feature_min_masks": 0,
|
37 |
+
"mask_feature_prob": 0.0,
|
38 |
+
"mask_time_length": 10,
|
39 |
+
"mask_time_min_masks": 2,
|
40 |
+
"mask_time_prob": 0.0,
|
41 |
+
"max_source_positions": 5000,
|
42 |
+
"model_type": "wav2vec2-bert",
|
43 |
+
"num_adapter_layers": 1,
|
44 |
+
"num_attention_heads": 16,
|
45 |
+
"num_codevector_groups": 2,
|
46 |
+
"num_codevectors_per_group": 320,
|
47 |
+
"num_hidden_layers": 24,
|
48 |
+
"num_negatives": 100,
|
49 |
+
"output_hidden_size": 1024,
|
50 |
+
"pad_token_id": 70,
|
51 |
+
"position_embeddings_type": "relative_key",
|
52 |
+
"proj_codevector_dim": 768,
|
53 |
+
"right_max_position_embeddings": 8,
|
54 |
+
"rotary_embedding_base": 10000,
|
55 |
+
"tdnn_dilation": [
|
56 |
+
1,
|
57 |
+
2,
|
58 |
+
3,
|
59 |
+
1,
|
60 |
+
1
|
61 |
+
],
|
62 |
+
"tdnn_dim": [
|
63 |
+
512,
|
64 |
+
512,
|
65 |
+
512,
|
66 |
+
512,
|
67 |
+
1500
|
68 |
+
],
|
69 |
+
"tdnn_kernel": [
|
70 |
+
5,
|
71 |
+
3,
|
72 |
+
3,
|
73 |
+
1,
|
74 |
+
1
|
75 |
+
],
|
76 |
+
"torch_dtype": "float32",
|
77 |
+
"transformers_version": "4.46.2",
|
78 |
+
"use_intermediate_ffn_before_adapter": false,
|
79 |
+
"use_weighted_layer_sum": false,
|
80 |
+
"vocab_size": 73,
|
81 |
+
"xvector_output_dim": 512
|
82 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f593772ff12079d44613bce31283edae568ea8f74ddf9edc3903352340b1fef0
|
3 |
+
size 2423113860
|
runs/Nov09_17-23-36_ubuntu-Standard-PC-Q35-ICH9-2009/events.out.tfevents.1731154685.ubuntu-Standard-PC-Q35-ICH9-2009.2249254.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b22b59c45e1c60bf0fd21edd5c2ba8dc667d03e79973f46c0cf85726dd1d7b4
|
3 |
+
size 7752
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"69": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"70": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"71": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"72": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02021c31c59b3cb9b187e8308f39887415c56166795156edc4411c8132138085
|
3 |
+
size 5304
|
vocab.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"[PAD]":
|
3 |
-
"[UNK]":
|
4 |
"|": 0,
|
5 |
"ಂ": 1,
|
6 |
"ಃ": 2,
|
@@ -21,52 +21,53 @@
|
|
21 |
"ಖ": 17,
|
22 |
"ಗ": 18,
|
23 |
"ಘ": 19,
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"
|
49 |
-
"
|
50 |
-
"
|
51 |
-
"
|
52 |
-
"
|
53 |
-
"
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"
|
57 |
-
"
|
58 |
-
"
|
59 |
-
"
|
60 |
-
"
|
61 |
-
"
|
62 |
-
"
|
63 |
-
"
|
64 |
-
"
|
65 |
-
"
|
66 |
-
"
|
67 |
-
"
|
68 |
-
"
|
69 |
-
"
|
70 |
-
"
|
71 |
-
"
|
|
|
72 |
}
|
|
|
1 |
{
|
2 |
+
"[PAD]": 70,
|
3 |
+
"[UNK]": 69,
|
4 |
"|": 0,
|
5 |
"ಂ": 1,
|
6 |
"ಃ": 2,
|
|
|
21 |
"ಖ": 17,
|
22 |
"ಗ": 18,
|
23 |
"ಘ": 19,
|
24 |
+
"ಙ": 20,
|
25 |
+
"ಚ": 21,
|
26 |
+
"ಛ": 22,
|
27 |
+
"ಜ": 23,
|
28 |
+
"ಝ": 24,
|
29 |
+
"ಞ": 25,
|
30 |
+
"ಟ": 26,
|
31 |
+
"ಠ": 27,
|
32 |
+
"ಡ": 28,
|
33 |
+
"ಢ": 29,
|
34 |
+
"ಣ": 30,
|
35 |
+
"ತ": 31,
|
36 |
+
"ಥ": 32,
|
37 |
+
"ದ": 33,
|
38 |
+
"ಧ": 34,
|
39 |
+
"ನ": 35,
|
40 |
+
"ಪ": 36,
|
41 |
+
"ಫ": 37,
|
42 |
+
"ಬ": 38,
|
43 |
+
"ಭ": 39,
|
44 |
+
"ಮ": 40,
|
45 |
+
"ಯ": 41,
|
46 |
+
"ರ": 42,
|
47 |
+
"ಱ": 43,
|
48 |
+
"ಲ": 44,
|
49 |
+
"ಳ": 45,
|
50 |
+
"ವ": 46,
|
51 |
+
"ಶ": 47,
|
52 |
+
"ಷ": 48,
|
53 |
+
"ಸ": 49,
|
54 |
+
"ಹ": 50,
|
55 |
+
"ಾ": 51,
|
56 |
+
"ಿ": 52,
|
57 |
+
"ೀ": 53,
|
58 |
+
"ು": 54,
|
59 |
+
"ೂ": 55,
|
60 |
+
"ೃ": 56,
|
61 |
+
"ೆ": 57,
|
62 |
+
"ೇ": 58,
|
63 |
+
"ೈ": 59,
|
64 |
+
"ೊ": 60,
|
65 |
+
"ೋ": 61,
|
66 |
+
"ೌ": 62,
|
67 |
+
"್": 63,
|
68 |
+
"ೕ": 64,
|
69 |
+
"ೖ": 65,
|
70 |
+
"": 66,
|
71 |
+
"": 67,
|
72 |
+
"": 68
|
73 |
}
|