Hugging Face's logo

CLEAR-Global
/
w2v-bert-2.0-hausa_579_993h_yourtts

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
CLEAR-Global/hausa_579_993h_yourtts
Generated from Trainer
Model card Files
xet
Metrics Community
ayymen commited on
Commit
d615d1d
·
verified ·
1 Parent(s): 68d1d69

Model save

Browse files
Files changed (3) hide show
  1. README.md +96 -0
  2. model.safetensors +1 -1
  3. runs/May31_09-36-14_hausa-synvoices-yourtts/events.out.tfevents.1748689800.hausa-synvoices-yourtts.57895.0 +2 -2
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_579_993h_yourtts
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_579_993h_yourtts
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: 0.2262
22
+ - Wer: 0.3255
23
+ - Cer: 0.1875
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: 16.0
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
59
+ |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
60
+ | 0.6846 | 0.2491 | 1000 | 0.4530 | 0.4190 | 0.2127 |
61
+ | 0.4048 | 0.4981 | 2000 | 0.3258 | 0.3781 | 0.2019 |
62
+ | 0.4272 | 0.7472 | 3000 | 0.2893 | 0.3688 | 0.1988 |
63
+ | 0.3224 | 0.9963 | 4000 | 0.2852 | 0.3530 | 0.1947 |
64
+ | 0.0543 | 1.2453 | 5000 | 0.2782 | 0.3550 | 0.1956 |
65
+ | 0.0747 | 1.4944 | 6000 | 0.2941 | 0.3611 | 0.1983 |
66
+ | 0.0416 | 1.7435 | 7000 | 0.2793 | 0.3421 | 0.1931 |
67
+ | 0.0476 | 1.9925 | 8000 | 0.2707 | 0.3435 | 0.1928 |
68
+ | 0.1736 | 2.2416 | 9000 | 0.2480 | 0.3365 | 0.1909 |
69
+ | 0.1951 | 2.4907 | 10000 | 0.2494 | 0.3372 | 0.1906 |
70
+ | 0.2139 | 2.7397 | 11000 | 0.2422 | 0.3349 | 0.1899 |
71
+ | 0.1895 | 2.9888 | 12000 | 0.2422 | 0.3332 | 0.1894 |
72
+ | 0.0223 | 3.2379 | 13000 | 0.2406 | 0.3336 | 0.1899 |
73
+ | 0.0201 | 3.4869 | 14000 | 0.2428 | 0.3294 | 0.1888 |
74
+ | 0.0169 | 3.7360 | 15000 | 0.2421 | 0.3312 | 0.1895 |
75
+ | 0.0282 | 3.9851 | 16000 | 0.2356 | 0.3330 | 0.1899 |
76
+ | 0.1346 | 4.2341 | 17000 | 0.2405 | 0.3331 | 0.1901 |
77
+ | 0.1021 | 4.4832 | 18000 | 0.2305 | 0.3276 | 0.1885 |
78
+ | 0.1164 | 4.7323 | 19000 | 0.2317 | 0.3324 | 0.1894 |
79
+ | 0.1136 | 4.9813 | 20000 | 0.2372 | 0.3311 | 0.1890 |
80
+ | 0.2131 | 5.2304 | 21000 | 0.2394 | 0.3278 | 0.1887 |
81
+ | 0.2363 | 5.4795 | 22000 | 0.2289 | 0.3255 | 0.1879 |
82
+ | 0.2423 | 5.7285 | 23000 | 0.2250 | 0.3253 | 0.1879 |
83
+ | 0.2533 | 5.9776 | 24000 | 0.2248 | 0.3237 | 0.1867 |
84
+ | 0.0307 | 6.2267 | 25000 | 0.2300 | 0.3268 | 0.1880 |
85
+ | 0.0322 | 6.4757 | 26000 | 0.2266 | 0.3262 | 0.1872 |
86
+ | 0.0346 | 6.7248 | 27000 | 0.2257 | 0.3281 | 0.1889 |
87
+ | 0.055 | 6.9738 | 28000 | 0.2315 | 0.3246 | 0.1875 |
88
+ | 0.1326 | 7.2229 | 29000 | 0.2262 | 0.3255 | 0.1875 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.48.1
94
+ - Pytorch 2.7.0+cu126
95
+ - Datasets 3.6.0
96
+ - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:574731d65b96f7074d3d51f0b013e94ceb651d6087cc3750f6966ef7d42d1f0b
3
  size 2423228660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812b5375a8ab12ccaf1fa6673ea4d1416fb1d872c171afc267bdf01f0d0d0bab
3
  size 2423228660
runs/May31_09-36-14_hausa-synvoices-yourtts/events.out.tfevents.1748689800.hausa-synvoices-yourtts.57895.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52ee1f5613ff949a1ec4a15a6f4d1a0a452f50c94e779058562353a86d872a3f
3
- size 6186084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f9700f6e8dff587b554745bca9308f217f3f8fe896b06234a6ff8915479f1f2
3
+ size 6186444