Hugging Face's logo

Ansu
/
Hubert-base-ASR-eu

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Model card Files
xet
Metrics Community
Ansu commited on
Commit
89ba541
·
verified ·
1 Parent(s): 4e0d430

End of training

Browse files
Files changed (6) hide show
  1. README.md +122 -0
  2. config.json +77 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +9 -0
  5. runs/Mar18_23-38-55_nej80nv-01113.itbatera.euskadi.eus/events.out.tfevents.1742337544.nej80nv-01113.itbatera.euskadi.eus.3864409.0 +3 -0
  6. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/hubert-base-ls960
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: Hubert-base-ASR-eu
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # Hubert-base-ASR-eu
18
+
19
+ This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1922
22
+ - Wer: 0.3154
23
+ - Cer: 0.0583
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 1e-05
43
+ - train_batch_size: 64
44
+ - eval_batch_size: 4
45
+ - seed: 42
46
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 10
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
+ |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
55
+ | 5.5577 | 0.1652 | 1000 | 3.5579 | 0.9999 | 0.9883 |
56
+ | 3.3467 | 0.3304 | 2000 | 2.9818 | 0.9999 | 0.9883 |
57
+ | 2.934 | 0.4955 | 3000 | 2.8354 | 0.9999 | 0.9883 |
58
+ | 2.8012 | 0.6607 | 4000 | 2.8179 | 0.9999 | 0.9883 |
59
+ | 2.7896 | 0.8259 | 5000 | 2.8299 | 0.9999 | 0.9883 |
60
+ | 1.4043 | 0.9911 | 6000 | 0.9904 | 0.9859 | 0.2788 |
61
+ | 0.903 | 1.1563 | 7000 | 0.5862 | 0.8110 | 0.1676 |
62
+ | 0.6955 | 1.3214 | 8000 | 0.4828 | 0.7192 | 0.1411 |
63
+ | 0.5764 | 1.4866 | 9000 | 0.4330 | 0.6535 | 0.1257 |
64
+ | 0.5195 | 1.6518 | 10000 | 0.3948 | 0.6083 | 0.1151 |
65
+ | 0.4949 | 1.8170 | 11000 | 0.3698 | 0.5676 | 0.1073 |
66
+ | 0.4481 | 1.9822 | 12000 | 0.3475 | 0.5343 | 0.1007 |
67
+ | 0.4251 | 2.1473 | 13000 | 0.3286 | 0.5162 | 0.0962 |
68
+ | 0.4257 | 2.3125 | 14000 | 0.3139 | 0.4933 | 0.0918 |
69
+ | 0.3982 | 2.4777 | 15000 | 0.3016 | 0.4780 | 0.0890 |
70
+ | 0.3672 | 2.6429 | 16000 | 0.2925 | 0.4616 | 0.0852 |
71
+ | 0.3741 | 2.8081 | 17000 | 0.2823 | 0.4504 | 0.0830 |
72
+ | 0.3991 | 2.9732 | 18000 | 0.2748 | 0.4372 | 0.0804 |
73
+ | 0.3624 | 3.1384 | 19000 | 0.2684 | 0.4293 | 0.0786 |
74
+ | 0.3362 | 3.3036 | 20000 | 0.2638 | 0.4180 | 0.0772 |
75
+ | 0.3209 | 3.4688 | 21000 | 0.2577 | 0.4072 | 0.0752 |
76
+ | 0.314 | 3.6340 | 22000 | 0.2498 | 0.4042 | 0.0744 |
77
+ | 0.3066 | 3.7991 | 23000 | 0.2452 | 0.3957 | 0.0730 |
78
+ | 0.3206 | 3.9643 | 24000 | 0.2466 | 0.3877 | 0.0717 |
79
+ | 0.3009 | 4.1295 | 25000 | 0.2396 | 0.3826 | 0.0708 |
80
+ | 0.3803 | 4.2947 | 26000 | 0.2391 | 0.3814 | 0.0705 |
81
+ | 0.2932 | 4.4599 | 27000 | 0.2334 | 0.3748 | 0.0692 |
82
+ | 0.2825 | 4.6250 | 28000 | 0.2292 | 0.3679 | 0.0679 |
83
+ | 0.2882 | 4.7902 | 29000 | 0.2253 | 0.3655 | 0.0675 |
84
+ | 0.2792 | 4.9554 | 30000 | 0.2233 | 0.3612 | 0.0667 |
85
+ | 0.2829 | 5.1206 | 31000 | 0.2224 | 0.3584 | 0.0664 |
86
+ | 0.2778 | 5.2858 | 32000 | 0.2221 | 0.3524 | 0.0652 |
87
+ | 0.2736 | 5.4509 | 33000 | 0.2160 | 0.3516 | 0.0647 |
88
+ | 0.2999 | 5.6161 | 34000 | 0.2156 | 0.3483 | 0.0646 |
89
+ | 0.2586 | 5.7813 | 35000 | 0.2149 | 0.3445 | 0.0634 |
90
+ | 0.2704 | 5.9465 | 36000 | 0.2132 | 0.3452 | 0.0635 |
91
+ | 0.2607 | 6.1117 | 37000 | 0.2112 | 0.3377 | 0.0626 |
92
+ | 0.2577 | 6.2768 | 38000 | 0.2074 | 0.3366 | 0.0620 |
93
+ | 0.2477 | 6.4420 | 39000 | 0.2064 | 0.3355 | 0.0617 |
94
+ | 0.2611 | 6.6072 | 40000 | 0.2062 | 0.3339 | 0.0615 |
95
+ | 0.2428 | 6.7724 | 41000 | 0.2044 | 0.3316 | 0.0611 |
96
+ | 0.246 | 6.9376 | 42000 | 0.2028 | 0.3314 | 0.0609 |
97
+ | 0.2664 | 7.1027 | 43000 | 0.2006 | 0.3295 | 0.0605 |
98
+ | 0.25 | 7.2679 | 44000 | 0.2027 | 0.3263 | 0.0601 |
99
+ | 0.2458 | 7.4331 | 45000 | 0.2009 | 0.3241 | 0.0599 |
100
+ | 0.2446 | 7.5983 | 46000 | 0.1995 | 0.3238 | 0.0598 |
101
+ | 0.2377 | 7.7635 | 47000 | 0.1997 | 0.3226 | 0.0594 |
102
+ | 0.2428 | 7.9286 | 48000 | 0.1981 | 0.3210 | 0.0592 |
103
+ | 0.2426 | 8.0938 | 49000 | 0.1964 | 0.3202 | 0.0591 |
104
+ | 0.253 | 8.2590 | 50000 | 0.1950 | 0.3191 | 0.0590 |
105
+ | 0.2635 | 8.4242 | 51000 | 0.1943 | 0.3191 | 0.0590 |
106
+ | 0.2789 | 8.5894 | 52000 | 0.1940 | 0.3175 | 0.0589 |
107
+ | 0.2608 | 8.7545 | 53000 | 0.1957 | 0.3173 | 0.0587 |
108
+ | 0.2231 | 8.9197 | 54000 | 0.1932 | 0.3167 | 0.0584 |
109
+ | 0.2406 | 9.0849 | 55000 | 0.1933 | 0.3164 | 0.0586 |
110
+ | 0.2347 | 9.2501 | 56000 | 0.1915 | 0.3161 | 0.0585 |
111
+ | 0.2502 | 9.4153 | 57000 | 0.1935 | 0.3153 | 0.0583 |
112
+ | 0.2353 | 9.5804 | 58000 | 0.1926 | 0.3154 | 0.0583 |
113
+ | 0.2358 | 9.7456 | 59000 | 0.1918 | 0.3156 | 0.0582 |
114
+ | 0.2395 | 9.9108 | 60000 | 0.1922 | 0.3154 | 0.0583 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.49.0
120
+ - Pytorch 2.6.0+cu124
121
+ - Datasets 3.3.2
122
+ - Tokenizers 0.21.0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/hubert-base-ls960",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "HubertForCTC"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
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_pos_batch_norm": false,
31
+ "conv_stride": [
32
+ 5,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2
39
+ ],
40
+ "ctc_loss_reduction": "mean",
41
+ "ctc_zero_infinity": false,
42
+ "do_stable_layer_norm": false,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.0,
46
+ "feat_extract_norm": "group",
47
+ "feat_proj_dropout": 0.1,
48
+ "feat_proj_layer_norm": true,
49
+ "final_dropout": 0.3,
50
+ "gradient_checkpointing": false,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_dropout_prob": 0.1,
54
+ "hidden_size": 768,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 3072,
57
+ "layer_norm_eps": 1e-05,
58
+ "layerdrop": 0.1,
59
+ "mask_feature_length": 10,
60
+ "mask_feature_min_masks": 0,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_masks": 2,
64
+ "mask_time_prob": 0.05,
65
+ "model_type": "hubert",
66
+ "num_attention_heads": 12,
67
+ "num_conv_pos_embedding_groups": 16,
68
+ "num_conv_pos_embeddings": 128,
69
+ "num_feat_extract_layers": 7,
70
+ "num_hidden_layers": 12,
71
+ "pad_token_id": 31,
72
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.49.0",
75
+ "use_weighted_layer_sum": false,
76
+ "vocab_size": 34
77
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0178b83529ab42d4169c7496ea4d371cbb6bbd2ac4f7eef4bcee08e3eb98aa1c
3
+ size 377616864
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": false,
8
+ "sampling_rate": 16000
9
+ }
runs/Mar18_23-38-55_nej80nv-01113.itbatera.euskadi.eus/events.out.tfevents.1742337544.nej80nv-01113.itbatera.euskadi.eus.3864409.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ccd7df7c2bd591546e78f5818027054ded63e0cb2f1eff610a25c067d2fbf4
3
+ size 158046
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2069d5c0e383bb2beca3646370515dbf2c15a1bf2a57e1b7e0193857878b4968
3
+ size 5368