speech-test commited on
Commit
7029728
1 Parent(s): 3e38008
Files changed (3) hide show
  1. config.json +110 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/unispeech-sat-base-plus",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "UniSpeechSatForAudioFrameClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 256,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": false,
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": false,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "group",
49
+ "feat_proj_dropout": 0.1,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.1,
54
+ "hidden_size": 768,
55
+ "id2label": {
56
+ "0": "speaker_0",
57
+ "1": "speaker_1"
58
+ },
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 3072,
61
+ "label2id": {
62
+ "speaker_0": 0,
63
+ "speaker_1": 1
64
+ },
65
+ "layer_norm_eps": 1e-05,
66
+ "layerdrop": 0.1,
67
+ "mask_feature_length": 10,
68
+ "mask_feature_prob": 0.0,
69
+ "mask_time_length": 10,
70
+ "mask_time_prob": 0.05,
71
+ "model_type": "unispeech-sat",
72
+ "num_attention_heads": 12,
73
+ "num_clusters": 504,
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": 12,
80
+ "num_negatives": 100,
81
+ "pad_token_id": 0,
82
+ "proj_codevector_dim": 256,
83
+ "tdnn_dilation": [
84
+ 1,
85
+ 2,
86
+ 3,
87
+ 1,
88
+ 1
89
+ ],
90
+ "tdnn_dim": [
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 512,
95
+ 1500
96
+ ],
97
+ "tdnn_kernel": [
98
+ 5,
99
+ 3,
100
+ 3,
101
+ 1,
102
+ 1
103
+ ],
104
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
105
+ "torch_dtype": "float32",
106
+ "transformers_version": "4.13.0.dev0",
107
+ "use_weighted_layer_sum": true,
108
+ "vocab_size": 32,
109
+ "xvector_output_dim": 512
110
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
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:fd69c3ce61ee7c06dc99ad997ce3c1296550b2a801a842baf8137210d9a19802
3
+ size 377577109