Hugging Face's logo

Kushala
/
wav2vec2-large-xls-r-300m-kushala

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Model card Files
xet
Metrics Community
1
Kushala commited on
Commit
c1cb3c2
·
1 Parent(s): 5ccf360

End of training

Browse files
Files changed (10) hide show
  1. config.json +79 -0
  2. preprocessor_config.json +9 -0
  3. pytorch_model.bin +3 -0
  4. runs/Aug28_16-55-09_ce637c436add/1661705739.4109116/events.out.tfevents.1661705739.ce637c436add.70.1 +3 -0
  5. runs/Aug28_16-55-09_ce637c436add/1661706002.401957/events.out.tfevents.1661706002.ce637c436add.70.2 +3 -0
  6. runs/Aug28_16-55-09_ce637c436add/events.out.tfevents.1661705739.ce637c436add.70.0 +3 -0
  7. runs/Aug28_17-00-40_ce637c436add/1661706053.6923034/events.out.tfevents.1661706053.ce637c436add.70.4 +3 -0
  8. runs/Aug28_17-00-40_ce637c436add/1661706147.299432/events.out.tfevents.1661706147.ce637c436add.70.5 +3 -0
  9. runs/Aug28_17-00-40_ce637c436add/events.out.tfevents.1661706053.ce637c436add.70.3 +3 -0
  10. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "codevector_dim": 768,
12
+ "contrastive_logits_temperature": 0.1,
13
+ "conv_bias": true,
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": true,
45
+ "eos_token_id": 2,
46
+ "feat_extract_activation": "gelu",
47
+ "feat_extract_dropout": 0.0,
48
+ "feat_extract_norm": "layer",
49
+ "feat_proj_dropout": 0.0,
50
+ "feat_quantizer_dropout": 0.0,
51
+ "final_dropout": 0.0,
52
+ "gradient_checkpointing": false,
53
+ "hidden_act": "gelu",
54
+ "hidden_dropout": 0.0,
55
+ "hidden_size": 1024,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "layer_norm_eps": 1e-05,
59
+ "layerdrop": 0.0,
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_prob": 0.05,
64
+ "model_type": "wav2vec2",
65
+ "num_attention_heads": 16,
66
+ "num_codevector_groups": 2,
67
+ "num_codevectors_per_group": 320,
68
+ "num_conv_pos_embedding_groups": 16,
69
+ "num_conv_pos_embeddings": 128,
70
+ "num_feat_extract_layers": 7,
71
+ "num_hidden_layers": 24,
72
+ "num_negatives": 100,
73
+ "pad_token_id": 38,
74
+ "proj_codevector_dim": 768,
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.11.3",
77
+ "use_weighted_layer_sum": false,
78
+ "vocab_size": 41
79
+ }
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": 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:e366d7b4ce788e0661cda9ec3c9d71b72a6ae850e7a2bb8efd2570ee661bb47a
3
+ size 1262091761
runs/Aug28_16-55-09_ce637c436add/1661705739.4109116/events.out.tfevents.1661705739.ce637c436add.70.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbbf2a0e8cd9c4b9cf231bc6b4cb14123b26c689be6204c2f4bb3b3a498aa81a
3
+ size 4564
runs/Aug28_16-55-09_ce637c436add/1661706002.401957/events.out.tfevents.1661706002.ce637c436add.70.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0c31aac4f8440d9a30a91014ba3af68531833aa63f104b29a93e6cb95441f4
3
+ size 4564
runs/Aug28_16-55-09_ce637c436add/events.out.tfevents.1661705739.ce637c436add.70.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d129370527a7955d76a5227ff6e90ac40eaff09435dead5a21ee42e11e155b
3
+ size 8400
runs/Aug28_17-00-40_ce637c436add/1661706053.6923034/events.out.tfevents.1661706053.ce637c436add.70.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dbf2d6f76888fe47f005d1d0e730dc780c5a89cea266b2e9874b0c5950f102c
3
+ size 4564
runs/Aug28_17-00-40_ce637c436add/1661706147.299432/events.out.tfevents.1661706147.ce637c436add.70.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f265a5a3ac41c6225c0fab7d5271b16962294793c9da400b9074b66da40b17b
3
+ size 4564
runs/Aug28_17-00-40_ce637c436add/events.out.tfevents.1661706053.ce637c436add.70.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e2718e4ece7f27764fc97cc1b044228632e8cf8fdb1053233fe6df4ebc1488
3
+ size 8744
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa9d91cebd481e3e15071ead92754e298e214d030954ed5a0daaf9625c0cd91
3
+ size 2863