Transformers
PyTorch
wav2vec2
pretraining
speech
xls_r
xls_r_pretrained
Inference Endpoints
patrickvonplaten commited on
Commit
0e04d23
1 Parent(s): 063f680
Files changed (3) hide show
  1. config.json +78 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForPreTraining"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "classifier_proj_size": 256,
10
+ "codevector_dim": 1024,
11
+ "contrastive_logits_temperature": 0.1,
12
+ "conv_bias": true,
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_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "sum",
41
+ "ctc_zero_infinity": false,
42
+ "diversity_loss_weight": 0.1,
43
+ "do_stable_layer_norm": true,
44
+ "eos_token_id": 2,
45
+ "feat_extract_activation": "gelu",
46
+ "feat_extract_dropout": 0.0,
47
+ "feat_extract_norm": "layer",
48
+ "feat_proj_dropout": 0.1,
49
+ "feat_quantizer_dropout": 0.0,
50
+ "final_dropout": 0.0,
51
+ "gradient_checkpointing": false,
52
+ "hidden_act": "gelu",
53
+ "hidden_dropout": 0.1,
54
+ "hidden_size": 1280,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 5120,
57
+ "layer_norm_eps": 1e-05,
58
+ "layerdrop": 0.1,
59
+ "mask_feature_length": 10,
60
+ "mask_feature_prob": 0.0,
61
+ "mask_time_length": 10,
62
+ "mask_time_prob": 0.075,
63
+ "model_type": "wav2vec2",
64
+ "num_attention_heads": 16,
65
+ "num_codevector_groups": 2,
66
+ "num_codevectors_per_group": 320,
67
+ "num_conv_pos_embedding_groups": 16,
68
+ "num_conv_pos_embeddings": 128,
69
+ "num_feat_extract_layers": 7,
70
+ "num_hidden_layers": 48,
71
+ "num_negatives": 100,
72
+ "pad_token_id": 0,
73
+ "proj_codevector_dim": 1024,
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.12.0.dev0",
76
+ "use_weighted_layer_sum": false,
77
+ "vocab_size": 32
78
+ }
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,
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 sha256:5af5567729e2a4421e6ff5b488838faa6712b5933346d284dcfa9d9f36b52c65
3
+ size 3862391172