Yehor Smoliakov commited on
Commit
1c55d4d
1 Parent(s): 1ac22db
.gitattributes CHANGED
@@ -1,6 +1,7 @@
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
 
4
  *.bz2 filter=lfs diff=lfs merge=lfs -text
5
  *.ckpt filter=lfs diff=lfs merge=lfs -text
6
  *.ftz filter=lfs diff=lfs merge=lfs -text
 
1
  *.7z filter=lfs diff=lfs merge=lfs -text
2
  *.arrow filter=lfs diff=lfs merge=lfs -text
3
  *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.binary filter=lfs diff=lfs merge=lfs -text
5
  *.bz2 filter=lfs diff=lfs merge=lfs -text
6
  *.ckpt filter=lfs diff=lfs merge=lfs -text
7
  *.ftz filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 39,
3
+ "<s>": 38
4
+ }
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.05,
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": true,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.05,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.0,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.05,
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": 2,
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": "4.37.0",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 40,
81
+ "xvector_output_dim": 512
82
+ }
language_model/lm.binary ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ff37f030c7e76538548010ef6fc13245b7cbe3aa198f5e3bc2e4faa6a5c3135
3
+ size 881279204
language_model/unigrams.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4e48f4434356a769f2d5475a93de24352072e89dc5996b5c29ee281cb64a57
3
+ size 2422978560
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2BertProcessor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "2": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "3": {
12
+ "content": "<unk>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "38": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "39": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<pad>",
42
+ "processor_class": "Wav2Vec2BertProcessor",
43
+ "replace_word_delimiter_char": " ",
44
+ "target_lang": null,
45
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
46
+ "unk_token": "<unk>",
47
+ "word_delimiter_token": "|"
48
+ }
vocab.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "'": 0,
3
+ "-": 1,
4
+ "<pad>": 2,
5
+ "<unk>": 3,
6
+ "|": 4,
7
+ "а": 5,
8
+ "б": 6,
9
+ "в": 7,
10
+ "г": 8,
11
+ "д": 9,
12
+ "е": 10,
13
+ "ж": 11,
14
+ "з": 12,
15
+ "и": 13,
16
+ "й": 14,
17
+ "к": 15,
18
+ "л": 16,
19
+ "м": 17,
20
+ "н": 18,
21
+ "о": 19,
22
+ "п": 20,
23
+ "р": 21,
24
+ "с": 22,
25
+ "т": 23,
26
+ "у": 24,
27
+ "ф": 25,
28
+ "х": 26,
29
+ "ц": 27,
30
+ "ч": 28,
31
+ "ш": 29,
32
+ "щ": 30,
33
+ "ь": 31,
34
+ "ю": 32,
35
+ "я": 33,
36
+ "є": 34,
37
+ "і": 35,
38
+ "ї": 36,
39
+ "ґ": 37
40
+ }