lucio commited on
Commit
dd2ced4
1 Parent(s): 4f090d8

Training in progress, step 500

Browse files
Files changed (17) hide show
  1. .gitignore +1 -0
  2. added_tokens.json +1 -0
  3. config.json +108 -0
  4. preprocessor_config.json +9 -0
  5. pytorch_model.bin +3 -0
  6. runs/Feb04_08-09-55_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962246.51635/events.out.tfevents.1643962246.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1195751.1 +3 -0
  7. runs/Feb04_08-09-55_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962246.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1195751.0 +3 -0
  8. runs/Feb04_08-11-34_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962316.8321793/events.out.tfevents.1643962316.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1196512.1 +3 -0
  9. runs/Feb04_08-11-34_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962316.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1196512.0 +3 -0
  10. runs/Feb04_08-12-46_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962413.1460874/events.out.tfevents.1643962413.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1197052.1 +3 -0
  11. runs/Feb04_08-12-46_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962413.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1197052.0 +3 -0
  12. runs/Feb04_08-15-32_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962578.6550806/events.out.tfevents.1643962578.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1198181.1 +3 -0
  13. runs/Feb04_08-15-32_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962578.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1198181.0 +3 -0
  14. special_tokens_map.json +1 -0
  15. tokenizer_config.json +1 -0
  16. training_args.bin +3 -0
  17. vocab.json +1 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 40, "</s>": 41}
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 64,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 39,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.17.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 42,
106
+ "xvector_output_dim": 512,
107
+ "zero_infinity": true
108
+ }
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": true,
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:afb0e7ffda879f5270fa52dc156834e2d5ad06c7ae971e1b62cca619780de3ee
3
+ size 1262095857
runs/Feb04_08-09-55_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962246.51635/events.out.tfevents.1643962246.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1195751.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf44a0386d13a3a5c76f2c5eede59e843c104f3ddf914cc0e0c7e7dd67e89e67
3
+ size 4802
runs/Feb04_08-09-55_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962246.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1195751.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8916ecf2a48c299a0db37548cdc0cd242dd4884bd0223d15903b1ed9e0a37f61
3
+ size 4756
runs/Feb04_08-11-34_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962316.8321793/events.out.tfevents.1643962316.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1196512.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f4527d4c04c47dff47f28aef97ddb037cf0cbdc381d848394f67e43ae40283
3
+ size 4802
runs/Feb04_08-11-34_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962316.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1196512.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5847b786888c124410f0f6c6ce8dd49aeb214b12641a14b2ab33e51e6825b959
3
+ size 4755
runs/Feb04_08-12-46_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962413.1460874/events.out.tfevents.1643962413.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1197052.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76136d34090929026319aaababd27cb091939131cdf911b80869b9d515e25c0
3
+ size 4802
runs/Feb04_08-12-46_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962413.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1197052.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eccc50538532c903f4c710a57826e15f6c166afe3df42e36ef68baef2a88323
3
+ size 4755
runs/Feb04_08-15-32_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643962578.6550806/events.out.tfevents.1643962578.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1198181.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d46edffaef664e941143ea163009f6999a4f0f06578a39f8ea68294a1dbda15
3
+ size 4802
runs/Feb04_08-15-32_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643962578.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.1198181.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a9e1de9ffeb4b5da7926b30a28e861ee9748f1f59af351798e8c0db691da34
3
+ size 5856
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./xls-r-kyrgiz-cv8", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cde060aa868bd66f6b2774ce16ec7877e122267f0549334cd1553b0d3ad50ad5
3
+ size 3055
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "й": 10, "к": 11, "л": 12, "м": 13, "н": 14, "о": 15, "п": 16, "р": 17, "с": 18, "т": 19, "у": 20, "ф": 21, "х": 22, "ц": 23, "ч": 24, "ш": 25, "щ": 26, "ъ": 27, "ы": 28, "ь": 29, "э": 30, "ю": 31, "я": 32, "ё": 33, "ң": 34, "ү": 35, "ӊ": 36, "ө": 37, "|": 0, "[UNK]": 38, "[PAD]": 39}