ylacombe HF staff commited on
Commit
f0f5bcc
1 Parent(s): 0ae22de

Training in progress, step 800

Browse files
config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ylacombe/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": true,
7
+ "apply_spec_augment": false,
8
+ "architectures": [
9
+ "Wav2Vec2BERTForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 768,
14
+ "codevector_dim": 768,
15
+ "conformer_conv_dropout": 0.1,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_depthwise_kernel_size": 31,
18
+ "ctc_loss_reduction": "mean",
19
+ "ctc_zero_infinity": false,
20
+ "diversity_loss_weight": 0.1,
21
+ "eos_token_id": 2,
22
+ "feat_proj_dropout": 0.0,
23
+ "feat_quantizer_dropout": 0.0,
24
+ "feature_projection_input_dim": 160,
25
+ "final_dropout": 0.1,
26
+ "hidden_act": "swish",
27
+ "hidden_dropout": 0.0,
28
+ "hidden_size": 1024,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 4096,
31
+ "layer_norm_eps": 1e-05,
32
+ "layerdrop": 0.0,
33
+ "left_max_position_embeddings": 64,
34
+ "mask_feature_length": 10,
35
+ "mask_feature_min_masks": 0,
36
+ "mask_feature_prob": 0.0,
37
+ "mask_time_length": 10,
38
+ "mask_time_min_masks": 2,
39
+ "mask_time_prob": 0.0,
40
+ "max_source_positions": 5000,
41
+ "model_type": "wav2vec2-bert",
42
+ "num_adapter_layers": 1,
43
+ "num_attention_heads": 16,
44
+ "num_codevector_groups": 2,
45
+ "num_codevectors_per_group": 320,
46
+ "num_hidden_layers": 24,
47
+ "num_negatives": 100,
48
+ "output_hidden_size": 1024,
49
+ "pad_token_id": 36,
50
+ "position_embeddings_type": "relative_key",
51
+ "proj_codevector_dim": 768,
52
+ "right_max_position_embeddings": 8,
53
+ "rotary_embedding_base": 10000,
54
+ "tdnn_dilation": [
55
+ 1,
56
+ 2,
57
+ 3,
58
+ 1,
59
+ 1
60
+ ],
61
+ "tdnn_dim": [
62
+ 512,
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 1500
67
+ ],
68
+ "tdnn_kernel": [
69
+ 5,
70
+ 3,
71
+ 3,
72
+ 1,
73
+ 1
74
+ ],
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.37.0.dev0",
77
+ "use_intermediate_ffn_before_adapter": false,
78
+ "use_weighted_layer_sum": false,
79
+ "vocab_size": 39,
80
+ "xvector_output_dim": 512
81
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a90d4ebd129a07bca3bd8d545771239a317a61adf170da0489cd3ae74a65b75a
3
+ size 2422974460
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000,
9
+ "stride": 2
10
+ }
runs/Jan10_19-24-06_dab203189bcf/events.out.tfevents.1704914696.dab203189bcf.723.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebbb7b5d11dab1d00ceb70132fa85a769d740286a1824199a51ff85494079da7
3
+ size 6907
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35908dc8cc12709665cea82ff0983935d6ed2b2a80b27948c6b3723e16520a8e
3
+ size 4728