patrickvonplaten commited on
Commit
88bd2e5
1 Parent(s): adf24b4
config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "adapter_kernel_size": 3,
4
+ "adapter_stride": 2,
5
+ "add_adapter": false,
6
+ "architectures": [
7
+ "Data2VecAudioForCTC"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 1,
11
+ "classifier_proj_size": 256,
12
+ "conv_bias": false,
13
+ "conv_dim": [
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512
21
+ ],
22
+ "conv_kernel": [
23
+ 10,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 3,
28
+ 2,
29
+ 2
30
+ ],
31
+ "conv_pos_kernel_size": 19,
32
+ "conv_stride": [
33
+ 5,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2
40
+ ],
41
+ "ctc_loss_reduction": "sum",
42
+ "ctc_zero_infinity": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_proj_dropout": 0.0,
46
+ "final_dropout": 0.1,
47
+ "hidden_act": "gelu",
48
+ "hidden_dropout": 0.1,
49
+ "hidden_size": 768,
50
+ "initializer_range": 0.02,
51
+ "intermediate_size": 3072,
52
+ "layer_norm_eps": 1e-05,
53
+ "layerdrop": 0.1,
54
+ "mask_feature_length": 10,
55
+ "mask_feature_min_masks": 0,
56
+ "mask_feature_prob": 0.0,
57
+ "mask_time_length": 10,
58
+ "mask_time_min_masks": 2,
59
+ "mask_time_prob": 0.05,
60
+ "model_type": "data2vec-audio",
61
+ "num_adapter_layers": 3,
62
+ "num_attention_heads": 12,
63
+ "num_conv_pos_embedding_groups": 16,
64
+ "num_conv_pos_embeddings": 5,
65
+ "num_feat_extract_layers": 7,
66
+ "num_hidden_layers": 12,
67
+ "output_hidden_size": 768,
68
+ "pad_token_id": 0,
69
+ "tdnn_dilation": [
70
+ 1,
71
+ 2,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "tdnn_dim": [
77
+ 512,
78
+ 512,
79
+ 512,
80
+ 512,
81
+ 1500
82
+ ],
83
+ "tdnn_kernel": [
84
+ 5,
85
+ 3,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.17.0.dev0",
92
+ "use_weighted_layer_sum": false,
93
+ "vocab_size": 32,
94
+ "xvector_output_dim": 512
95
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0f29b6b713f88df166a3edfe8db2657fcc9f728d32d68793de5109efacc52d
3
+ size 372850161
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": "|", "replace_word_delimiter_char": " ", "return_attention_mask": false, "do_normalize": true, "special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/60230682499b8486f2a3109ba26ac7395fd4eba61426f05432329ccbfac7c190.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "name_or_path": "facebook/wav2vec2-large-lv60", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}
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}