Hugging Face's logo

CLEAR-Global
/
w2v-bert-2.0-igbo_naijavoices_500h

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Model card Files Metrics Community
ayymen commited on
Commit
ffec260
·
verified ·
1 Parent(s): dc29e6a

Model save

Browse files
Files changed (3) hide show
  1. README.md +100 -0
  2. model.safetensors +1 -1
  3. runs/Jul18_00-07-43_gf-asr-training-2a100/events.out.tfevents.1752797745.gf-asr-training-2a100.244221.0 +2 -2
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: facebook/w2v-bert-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: w2v-bert-2.0-igbo_naijavoices_500h
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
+ # w2v-bert-2.0-igbo_naijavoices_500h
18
+
19
+ This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2218
22
+ - Wer: 0.2455
23
+ - Cer: 0.1105
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: 3e-05
43
+ - train_batch_size: 160
44
+ - eval_batch_size: 160
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 2
48
+ - total_train_batch_size: 320
49
+ - total_eval_batch_size: 320
50
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
+ - num_epochs: 50.0
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.923 | 0.6901 | 1000 | 0.6313 | 0.5401 | 0.2069 |
61
+ | 0.4648 | 1.3803 | 2000 | 0.4222 | 0.3868 | 0.1549 |
62
+ | 0.3635 | 2.0704 | 3000 | 0.3582 | 0.3499 | 0.1434 |
63
+ | 0.3388 | 2.7605 | 4000 | 0.3368 | 0.3322 | 0.1383 |
64
+ | 0.2967 | 3.4507 | 5000 | 0.3141 | 0.3191 | 0.1366 |
65
+ | 0.2738 | 4.1408 | 6000 | 0.3041 | 0.3151 | 0.1328 |
66
+ | 0.3146 | 4.8309 | 7000 | 0.2972 | 0.3091 | 0.1297 |
67
+ | 0.2612 | 5.5210 | 8000 | 0.2856 | 0.2998 | 0.1312 |
68
+ | 0.282 | 6.2112 | 9000 | 0.2873 | 0.3001 | 0.1300 |
69
+ | 0.2989 | 6.9013 | 10000 | 0.2864 | 0.2959 | 0.1309 |
70
+ | 0.2633 | 7.5914 | 11000 | 0.2660 | 0.2883 | 0.1242 |
71
+ | 0.2471 | 8.2816 | 12000 | 0.2674 | 0.2905 | 0.1263 |
72
+ | 0.2746 | 8.9717 | 13000 | 0.2671 | 0.2822 | 0.1224 |
73
+ | 0.2754 | 9.6618 | 14000 | 0.2617 | 0.2833 | 0.1234 |
74
+ | 0.2881 | 10.3520 | 15000 | 0.2596 | 0.2833 | 0.1229 |
75
+ | 0.2717 | 11.0421 | 16000 | 0.2524 | 0.2760 | 0.1221 |
76
+ | 0.2204 | 11.7322 | 17000 | 0.2513 | 0.2720 | 0.1197 |
77
+ | 0.2429 | 12.4224 | 18000 | 0.2530 | 0.2738 | 0.1203 |
78
+ | 0.2429 | 13.1125 | 19000 | 0.2511 | 0.2745 | 0.1194 |
79
+ | 0.2449 | 13.8026 | 20000 | 0.2555 | 0.2748 | 0.1209 |
80
+ | 0.2053 | 14.4928 | 21000 | 0.2464 | 0.2719 | 0.1181 |
81
+ | 0.222 | 15.1829 | 22000 | 0.2428 | 0.2659 | 0.1195 |
82
+ | 0.1874 | 15.8730 | 23000 | 0.2418 | 0.2609 | 0.1156 |
83
+ | 0.1924 | 16.5631 | 24000 | 0.2363 | 0.2675 | 0.1176 |
84
+ | 0.1855 | 17.2533 | 25000 | 0.2336 | 0.2629 | 0.1151 |
85
+ | 0.2172 | 17.9434 | 26000 | 0.2302 | 0.2633 | 0.1153 |
86
+ | 0.2074 | 18.6335 | 27000 | 0.2345 | 0.2588 | 0.1161 |
87
+ | 0.1589 | 19.3237 | 28000 | 0.2204 | 0.2474 | 0.1137 |
88
+ | 0.1382 | 20.0138 | 29000 | 0.2279 | 0.2531 | 0.1127 |
89
+ | 0.1525 | 20.7039 | 30000 | 0.2284 | 0.2550 | 0.1128 |
90
+ | 0.149 | 21.3941 | 31000 | 0.2221 | 0.2509 | 0.1122 |
91
+ | 0.1193 | 22.0842 | 32000 | 0.2229 | 0.2482 | 0.1113 |
92
+ | 0.1245 | 22.7743 | 33000 | 0.2218 | 0.2455 | 0.1105 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.48.1
98
+ - Pytorch 2.7.1+cu126
99
+ - Datasets 4.0.0
100
+ - Tokenizers 0.21.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14f1d5e58b5f10184e7b5478c030123fffe1588a59ba51b20cd9d1f896b10392
3
  size 2423097460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7509586c5216f95072ea662d0070b30887bf5dbac55a82996f8927e20ee6fef8
3
  size 2423097460
runs/Jul18_00-07-43_gf-asr-training-2a100/events.out.tfevents.1752797745.gf-asr-training-2a100.244221.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f15ccf46514b937b0e90acd031aaea68a2347180464de8ba9ae75260c2b0cb20
3
- size 7047565
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c2d3c0fdad78baf946bf2b23d8948cdc1c15214512c14a8c1164e3c0bc46e1
3
+ size 7047925