Transformers
PyTorch
wav2vec2
pretraining
speech
xls_r
xls_r_pretrained
Inference Endpoints
patrickvonplaten commited on
Commit
df85d9c
1 Parent(s): fdf300d
Files changed (3) hide show
  1. config.json +75 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "codevector_dim": 1024,
10
+ "contrastive_logits_temperature": 0.1,
11
+ "conv_bias": true,
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
+ "ctc_zero_infinity": false,
41
+ "diversity_loss_weight": 0.1,
42
+ "do_stable_layer_norm": true,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.0,
46
+ "feat_extract_norm": "layer",
47
+ "feat_proj_dropout": 0.1,
48
+ "feat_quantizer_dropout": 0.0,
49
+ "final_dropout": 0.0,
50
+ "gradient_checkpointing": false,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_size": 1920,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 7680,
56
+ "layer_norm_eps": 1e-05,
57
+ "layerdrop": 0.1,
58
+ "mask_feature_length": 10,
59
+ "mask_feature_prob": 0.0,
60
+ "mask_time_length": 10,
61
+ "mask_time_prob": 0.075,
62
+ "model_type": "wav2vec2",
63
+ "num_attention_heads": 16,
64
+ "num_codevector_groups": 2,
65
+ "num_codevectors_per_group": 320,
66
+ "num_conv_pos_embedding_groups": 16,
67
+ "num_conv_pos_embeddings": 128,
68
+ "num_feat_extract_layers": 7,
69
+ "num_hidden_layers": 48,
70
+ "num_negatives": 100,
71
+ "pad_token_id": 0,
72
+ "proj_codevector_dim": 1024,
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.12.0.dev0"
75
+ }
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:d0309bd36442d439dca441c6d3edf96988118b3a251ac37c5bcefdfc2312dfa5
3
+ size 8652066332