patrickvonplaten commited on
Commit
9dec1ac
1 Parent(s): 942b5db
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "architectures": [
4
+ "UniSpeechSatForCTC"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "bos_token_id": 1,
8
+ "classifier_proj_size": 256,
9
+ "codevector_dim": 256,
10
+ "contrastive_logits_temperature": 0.1,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "diversity_loss_weight": 0.1,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.1,
46
+ "feat_quantizer_dropout": 0.0,
47
+ "final_dropout": 0.1,
48
+ "freeze_feat_extract_train": true,
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": 3072,
54
+ "layer_norm_eps": 1e-05,
55
+ "layerdrop": 0.1,
56
+ "mask_feature_length": 10,
57
+ "mask_feature_prob": 0.0,
58
+ "mask_time_length": 10,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "unispeech-sat",
61
+ "num_attention_heads": 12,
62
+ "num_clusters": 504,
63
+ "num_codevector_groups": 2,
64
+ "num_codevectors_per_group": 320,
65
+ "num_conv_pos_embedding_groups": 16,
66
+ "num_conv_pos_embeddings": 128,
67
+ "num_feat_extract_layers": 7,
68
+ "num_hidden_layers": 12,
69
+ "num_negatives": 100,
70
+ "pad_token_id": 0,
71
+ "proj_codevector_dim": 256,
72
+ "torch_dtype": "float32",
73
+ "transformers_version": "4.12.0.dev0",
74
+ "use_weighted_layer_sum": false,
75
+ "vocab_size": 32
76
+ }
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": 0.0,
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:f03b2cfcabd84c022aa50616eb62993513a6f4e5a1742477c97b5296b9c054aa
3
+ size 377674604
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": "|", "return_attention_mask": false, "do_normalize": true, "special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/6e305f345764752bb3b07ab4eaeebe722f895e6f1286d4821a76801f05282e5c.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "tokenizer_file": null, "name_or_path": "facebook/wav2vec2-base-100h", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
vocab.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}