Sakai Yusuke commited on
Commit
7a9c2cd
1 Parent(s): 04e7d8e

add models

Browse files
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "checkpoint-600",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
14
+ "conv_dim": [
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512
22
+ ],
23
+ "conv_kernel": [
24
+ 10,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 3,
29
+ 2,
30
+ 2
31
+ ],
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "mean",
42
+ "ctc_zero_infinity": false,
43
+ "diversity_loss_weight": 0.1,
44
+ "do_stable_layer_norm": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.0,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "gradient_checkpointing": false,
53
+ "hidden_act": "gelu",
54
+ "hidden_dropout": 0.1,
55
+ "hidden_size": 1024,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.1,
60
+ "mask_channel_length": 10,
61
+ "mask_channel_min_space": 1,
62
+ "mask_channel_other": 0.0,
63
+ "mask_channel_prob": 0.0,
64
+ "mask_channel_selection": "static",
65
+ "mask_feature_length": 10,
66
+ "mask_feature_prob": 0.0,
67
+ "mask_time_length": 10,
68
+ "mask_time_min_space": 1,
69
+ "mask_time_other": 0.0,
70
+ "mask_time_prob": 0.05,
71
+ "mask_time_selection": "static",
72
+ "model_type": "wav2vec2",
73
+ "num_attention_heads": 16,
74
+ "num_codevector_groups": 2,
75
+ "num_codevectors_per_group": 320,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 24,
80
+ "num_negatives": 100,
81
+ "pad_token_id": 81,
82
+ "proj_codevector_dim": 768,
83
+ "torch_dtype": "float32",
84
+ "transformers_version": "4.11.3",
85
+ "use_weighted_layer_sum": false,
86
+ "vocab_size": 82
87
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d32c4a84cb3972806d9a17c4c3d03cb2b5c7fcc626f62fe9c858c66ef8ac8fa
3
+ size 1262254001
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
+ {"q": 0, "ɴ": 1, "ϊ": 2, "ð": 3, "ɬ": 4, "ɑ": 5, "l": 6, "t͡ɕ": 7, "d͡ʐ": 8, "n": 9, "e": 10, "ʼ": 11, "ʂ": 12, "ʑ": 13, "ɨ": 14, "ɟ": 15, "m": 16, "ɸ": 17, "a": 18, "ɮ": 19, "k": 20, "ʋ": 21, "ç": 22, "p": 23, "'": 24, "ː": 25, "ʃ": 26, "r": 27, "ɣ": 28, " ": 29, "ɒ": 30, "æ": 31, "#": 32, "t͡ʂ": 33, "b": 34, "ʒ": 35, "s": 36, "ɾ": 37, "f": 38, "ʎ": 39, "θ": 40, "t": 41, "ʐ": 42, "y": 43, "o": 44, "ɲ": 45, "d͡z": 46, "ʔ": 47, "ø": 48, "̇": 49, "ɛ": 50, "ʝ": 51, "ħ": 52, "d": 53, "ɡ": 54, "ɕ": 55, "á": 56, "ǃ": 57, "ɔ": 58, "ʲ": 59, "g": 60, "é": 61, "ŋ": 62, "ɱ": 63, "z": 64, "t͡s": 65, "x": 66, "c": 67, "d͡ʑ": 68, "ɯ": 69, "ΐ": 70, "w": 71, "v": 72, "ǀ": 73, "j": 74, "ϋ": 75, "i": 76, "u": 77, "h": 78, "̃": 79, "[UNK]": 80, "[PAD]": 81}