Hugging Face's logo

Eyesiga
/
Runyakore_XlSR_WAV2VEC

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Eyesiga commited on
Commit
22f3024
•
1 Parent(s): dc63cd6

Training in progress, step 1000

Browse files
Files changed (8) hide show
  1. config.json +120 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +9 -0
  4. runs/Feb06_16-34-15_b3ce89a1c4cd/events.out.tfevents.1707237469.b3ce89a1c4cd.2195.0 +3 -0
  5. runs/Feb06_16-38-13_b3ce89a1c4cd/events.out.tfevents.1707237699.b3ce89a1c4cd.2195.1 +3 -0
  6. runs/Feb06_16-42-00_b3ce89a1c4cd/events.out.tfevents.1707237934.b3ce89a1c4cd.2195.2 +3 -0
  7. runs/Feb06_16-47-28_b3ce89a1c4cd/events.out.tfevents.1707238264.b3ce89a1c4cd.2195.3 +3 -0
  8. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
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
+ "Wav2Vec2ForCTC"
11
+ ],
12
+ "attention_dropout": 0.1,
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": 0.1,
54
+ "feat_quantizer_dropout": 0.0,
55
+ "final_dropout": 0.0,
56
+ "forced_decoder_ids": null,
57
+ "gradient_checkpointing": false,
58
+ "hidden_act": "gelu",
59
+ "hidden_dropout": 0.1,
60
+ "hidden_size": 1024,
61
+ "initializer_range": 0.02,
62
+ "intermediate_size": 4096,
63
+ "layer_norm_eps": 1e-05,
64
+ "layerdrop": 0.1,
65
+ "mask_channel_length": 10,
66
+ "mask_channel_min_space": 1,
67
+ "mask_channel_other": 0.0,
68
+ "mask_channel_prob": 0.0,
69
+ "mask_channel_selection": "static",
70
+ "mask_feature_length": 10,
71
+ "mask_feature_min_masks": 0,
72
+ "mask_feature_prob": 0.0,
73
+ "mask_time_length": 10,
74
+ "mask_time_min_masks": 2,
75
+ "mask_time_min_space": 1,
76
+ "mask_time_other": 0.0,
77
+ "mask_time_prob": 0.05,
78
+ "mask_time_selection": "static",
79
+ "model_type": "wav2vec2",
80
+ "num_adapter_layers": 3,
81
+ "num_attention_heads": 16,
82
+ "num_codevector_groups": 2,
83
+ "num_codevectors_per_group": 320,
84
+ "num_conv_pos_embedding_groups": 16,
85
+ "num_conv_pos_embeddings": 128,
86
+ "num_feat_extract_layers": 7,
87
+ "num_hidden_layers": 24,
88
+ "num_negatives": 100,
89
+ "output_hidden_size": 1024,
90
+ "pad_token_id": 34,
91
+ "proj_codevector_dim": 768,
92
+ "suppress_tokens": [],
93
+ "tdnn_dilation": [
94
+ 1,
95
+ 2,
96
+ 3,
97
+ 1,
98
+ 1
99
+ ],
100
+ "tdnn_dim": [
101
+ 512,
102
+ 512,
103
+ 512,
104
+ 512,
105
+ 1500
106
+ ],
107
+ "tdnn_kernel": [
108
+ 5,
109
+ 3,
110
+ 3,
111
+ 1,
112
+ 1
113
+ ],
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.37.2",
116
+ "use_cache": false,
117
+ "use_weighted_layer_sum": false,
118
+ "vocab_size": 37,
119
+ "xvector_output_dim": 512
120
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a88d78b15d7b23a789c7f9b08f5d4dde6e3d2577a3f068daea3020fecf4a00
3
+ size 1261959180
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
+ }
runs/Feb06_16-34-15_b3ce89a1c4cd/events.out.tfevents.1707237469.b3ce89a1c4cd.2195.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73dd0d6a00a36ee2f957a387ff45f0e989977f83b3d188602f424a6c314509c9
3
+ size 6123
runs/Feb06_16-38-13_b3ce89a1c4cd/events.out.tfevents.1707237699.b3ce89a1c4cd.2195.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca0575a614a60d949e3aaf02d59fa930c563e02a8bcdbab2f540e428ffccf7d
3
+ size 6122
runs/Feb06_16-42-00_b3ce89a1c4cd/events.out.tfevents.1707237934.b3ce89a1c4cd.2195.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4674b337a3adfb12d11dcf6c2d5ee72db2f0d0f06bd453e7bef34eaf00c844d8
3
+ size 6122
runs/Feb06_16-47-28_b3ce89a1c4cd/events.out.tfevents.1707238264.b3ce89a1c4cd.2195.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29296359d6b5caaf035a93d07093c642e814fd24ef859700f97077cd597449f1
3
+ size 12705
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:434638faa0ffe1920bcd669ba76f11609f5edcd846abc5320fe1c620e31a6862
3
+ size 4728