Hugging Face's logo

CLEAR-Global
/
w2v-bert-2.0-hausa_250_250h_yourtts

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
CLEAR-Global/hausa_250_250h_yourtts
Generated from Trainer
Model card Files Metrics Community
ayymen commited on
Commit
78acc93
·
verified ·
1 Parent(s): 20b6576

Model save

Browse files
Files changed (3) hide show
  1. README.md +92 -0
  2. model.safetensors +1 -1
  3. runs/May28_21-42-57_synvoices-hausa-yourtss/events.out.tfevents.1748468837.synvoices-hausa-yourtss.57965.0 +2 -2
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-hausa_250_250h_yourtts-v2
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-hausa_250_250h_yourtts-v2
18
+
19
+ This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2410
22
+ - Wer: 0.3277
23
+ - Cer: 0.1881
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
+ | 0.5843 | 0.7225 | 1000 | 0.4228 | 0.4167 | 0.2123 |
61
+ | 0.2847 | 1.4451 | 2000 | 0.3274 | 0.3731 | 0.2006 |
62
+ | 0.0642 | 2.1676 | 3000 | 0.2891 | 0.3553 | 0.1963 |
63
+ | 0.082 | 2.8902 | 4000 | 0.2788 | 0.3512 | 0.1944 |
64
+ | 0.2373 | 3.6127 | 5000 | 0.2654 | 0.3462 | 0.1927 |
65
+ | 0.186 | 4.3353 | 6000 | 0.2633 | 0.3464 | 0.1930 |
66
+ | 0.0351 | 5.0578 | 7000 | 0.2603 | 0.3416 | 0.1921 |
67
+ | 0.0405 | 5.7803 | 8000 | 0.2670 | 0.3467 | 0.1932 |
68
+ | 0.1905 | 6.5029 | 9000 | 0.2480 | 0.3350 | 0.1904 |
69
+ | 0.1314 | 7.2254 | 10000 | 0.2616 | 0.3349 | 0.1907 |
70
+ | 0.1442 | 7.9480 | 11000 | 0.2596 | 0.3376 | 0.1914 |
71
+ | 0.0301 | 8.6705 | 12000 | 0.2439 | 0.3336 | 0.1897 |
72
+ | 0.1593 | 9.3931 | 13000 | 0.2410 | 0.3342 | 0.1898 |
73
+ | 0.1037 | 10.1156 | 14000 | 0.2461 | 0.3331 | 0.1905 |
74
+ | 0.0634 | 10.8382 | 15000 | 0.2598 | 0.3303 | 0.1896 |
75
+ | 0.0555 | 11.5607 | 16000 | 0.2400 | 0.3328 | 0.1899 |
76
+ | 0.1657 | 12.2832 | 17000 | 0.2437 | 0.3318 | 0.1896 |
77
+ | 0.0588 | 13.0058 | 18000 | 0.2386 | 0.3334 | 0.1904 |
78
+ | 0.058 | 13.7283 | 19000 | 0.2453 | 0.3294 | 0.1888 |
79
+ | 0.1711 | 14.4509 | 20000 | 0.2383 | 0.3317 | 0.1898 |
80
+ | 0.1441 | 15.1734 | 21000 | 0.2432 | 0.3324 | 0.1900 |
81
+ | 0.1502 | 15.8960 | 22000 | 0.2403 | 0.3287 | 0.1891 |
82
+ | 0.0333 | 16.6185 | 23000 | 0.2399 | 0.3313 | 0.1895 |
83
+ | 0.1604 | 17.3410 | 24000 | 0.2430 | 0.3273 | 0.1887 |
84
+ | 0.1162 | 18.0636 | 25000 | 0.2410 | 0.3277 | 0.1881 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.48.1
90
+ - Pytorch 2.7.0+cu126
91
+ - Datasets 3.6.0
92
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53a225ae5371fd04772ae611f0727e3c28a076b70c12662d7bee67155ee991b4
3
  size 2423220460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:884143abb7c315822a0c651d5798dc5179626dc8339e86879da69d74cf104179
3
  size 2423220460
runs/May28_21-42-57_synvoices-hausa-yourtss/events.out.tfevents.1748468837.synvoices-hausa-yourtss.57965.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37f056e23e2bd717ffc532b37511fa8d0683f3b64991c9c8c450148c73d518d3
3
- size 5324607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db3c41b0b9e42951e0e6baa41d2deeb52e9238f45cda9e1baf7365ade3ea00d0
3
+ size 5324967