smerchi commited on
Commit
a8345f9
1 Parent(s): ee83946

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "boumehdi/wav2vec2-large-xlsr-moroccan-darija",
3
+ "activation_dropout": 0.0,
4
+ "adapter_attn_dim": null,
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": true,
9
+ "architectures": [
10
+ "Wav2Vec2ForSequenceClassification"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 256,
15
+ "codevector_dim": 768,
16
+ "contrastive_logits_temperature": 0.1,
17
+ "conv_bias": true,
18
+ "conv_dim": [
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512
26
+ ],
27
+ "conv_kernel": [
28
+ 10,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 3,
33
+ 2,
34
+ 2
35
+ ],
36
+ "conv_stride": [
37
+ 5,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2,
43
+ 2
44
+ ],
45
+ "ctc_loss_reduction": "mean",
46
+ "ctc_zero_infinity": false,
47
+ "diversity_loss_weight": 0.1,
48
+ "do_stable_layer_norm": true,
49
+ "eos_token_id": 2,
50
+ "feat_extract_activation": "gelu",
51
+ "feat_extract_dropout": 0.0,
52
+ "feat_extract_norm": "layer",
53
+ "feat_proj_dropout": 0.0,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "gradient_checkpointing": false,
57
+ "hidden_act": "gelu",
58
+ "hidden_dropout": 0.0,
59
+ "hidden_size": 1024,
60
+ "id2label": {
61
+ "0": "Autre",
62
+ "1": "*6"
63
+ },
64
+ "initializer_range": 0.02,
65
+ "intermediate_size": 4096,
66
+ "label2id": {
67
+ "*6": "1",
68
+ "Autre": "0"
69
+ },
70
+ "layer_norm_eps": 1e-05,
71
+ "layerdrop": 0.0,
72
+ "mask_channel_length": 10,
73
+ "mask_channel_min_space": 1,
74
+ "mask_channel_other": 0.0,
75
+ "mask_channel_prob": 0.0,
76
+ "mask_channel_selection": "static",
77
+ "mask_feature_length": 10,
78
+ "mask_feature_min_masks": 0,
79
+ "mask_feature_prob": 0.0,
80
+ "mask_time_length": 10,
81
+ "mask_time_min_masks": 2,
82
+ "mask_time_min_space": 1,
83
+ "mask_time_other": 0.0,
84
+ "mask_time_prob": 0.05,
85
+ "mask_time_selection": "static",
86
+ "model_type": "wav2vec2",
87
+ "num_adapter_layers": 3,
88
+ "num_attention_heads": 16,
89
+ "num_codevector_groups": 2,
90
+ "num_codevectors_per_group": 320,
91
+ "num_conv_pos_embedding_groups": 16,
92
+ "num_conv_pos_embeddings": 128,
93
+ "num_feat_extract_layers": 7,
94
+ "num_hidden_layers": 24,
95
+ "num_negatives": 100,
96
+ "output_hidden_size": 1024,
97
+ "pad_token_id": 64,
98
+ "proj_codevector_dim": 768,
99
+ "tdnn_dilation": [
100
+ 1,
101
+ 2,
102
+ 3,
103
+ 1,
104
+ 1
105
+ ],
106
+ "tdnn_dim": [
107
+ 512,
108
+ 512,
109
+ 512,
110
+ 512,
111
+ 1500
112
+ ],
113
+ "tdnn_kernel": [
114
+ 5,
115
+ 3,
116
+ 3,
117
+ 1,
118
+ 1
119
+ ],
120
+ "torch_dtype": "float32",
121
+ "transformers_version": "4.41.2",
122
+ "use_weighted_layer_sum": false,
123
+ "vocab_size": 65,
124
+ "xvector_output_dim": 512
125
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef64a211f457926c85216778994f6eb0a54b2c875fd97f8421bf080b727cac9
3
+ size 1262859296
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0a43a3da0f9e47aa83ed32e750238b4f8130178e759a391af4d16daea72c49
3
+ size 5112