Hugging Face's logo

TopSlayer
/
model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
TopSlayer commited on
Commit
337573b
·
verified ·
1 Parent(s): 98edcd9

End of training

Browse files
Files changed (3) hide show
  1. README.md +33 -8
  2. model.safetensors +1 -1
  3. runs/Jul20_18-36-31_cs-01k0mh641vxyz3b3yz4ymxh86p/events.out.tfevents.1753036864.cs-01k0mh641vxyz3b3yz4ymxh86p.8010.0 +2 -2
README.md CHANGED
@@ -4,6 +4,8 @@ license: apache-2.0
4
  base_model: facebook/wav2vec2-xls-r-300m
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: model
9
  results: []
@@ -15,6 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
15
  # model
16
 
17
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
 
 
 
 
18
 
19
  ## Model description
20
 
@@ -33,26 +39,45 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 5e-05
37
- - train_batch_size: 8
38
- - eval_batch_size: 8
39
  - seed: 42
40
- - gradient_accumulation_steps: 4
41
- - total_train_batch_size: 32
42
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - lr_scheduler_warmup_ratio: 0.1
45
  - lr_scheduler_warmup_steps: 1000
46
- - num_epochs: 60
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
 
53
  ### Framework versions
54
 
55
  - Transformers 4.51.3
56
- - Pytorch 2.7.1+cu118
57
  - Datasets 4.0.0
58
  - Tokenizers 0.21.2
 
4
  base_model: facebook/wav2vec2-xls-r-300m
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: model
11
  results: []
 
17
  # model
18
 
19
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.5326
22
+ - Wer: 0.7415
23
+ - Cer: 0.2170
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 0.0001
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 16
45
  - seed: 42
 
 
46
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
 
48
  - lr_scheduler_warmup_steps: 1000
49
+ - num_epochs: 100
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
55
+ |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|
56
+ | 7.5237 | 4.9751 | 1000 | 3.8439 | 1.0 | 1.0 |
57
+ | 2.6634 | 9.9502 | 2000 | 1.3226 | 0.9684 | 0.3816 |
58
+ | 1.4289 | 14.9254 | 3000 | 1.0885 | 0.9007 | 0.2868 |
59
+ | 1.1709 | 19.9005 | 4000 | 1.0005 | 0.8495 | 0.2609 |
60
+ | 1.0088 | 24.8756 | 5000 | 1.0035 | 0.8149 | 0.2409 |
61
+ | 0.8933 | 29.8507 | 6000 | 1.0224 | 0.8326 | 0.2442 |
62
+ | 0.7856 | 34.8259 | 7000 | 1.0826 | 0.7804 | 0.2334 |
63
+ | 0.7118 | 39.8010 | 8000 | 1.1140 | 0.7814 | 0.2331 |
64
+ | 0.6442 | 44.7761 | 9000 | 1.1626 | 0.7857 | 0.2319 |
65
+ | 0.5947 | 49.7512 | 10000 | 1.1976 | 0.7798 | 0.2318 |
66
+ | 0.5439 | 54.7264 | 11000 | 1.2419 | 0.7835 | 0.2234 |
67
+ | 0.4957 | 59.7015 | 12000 | 1.3443 | 0.7523 | 0.2220 |
68
+ | 0.4581 | 64.6766 | 13000 | 1.3568 | 0.7704 | 0.2216 |
69
+ | 0.4346 | 69.6517 | 14000 | 1.3921 | 0.7643 | 0.2227 |
70
+ | 0.4044 | 74.6269 | 15000 | 1.4720 | 0.7572 | 0.2208 |
71
+ | 0.3794 | 79.6020 | 16000 | 1.4621 | 0.7496 | 0.2189 |
72
+ | 0.3586 | 84.5771 | 17000 | 1.4913 | 0.7460 | 0.2198 |
73
+ | 0.3432 | 89.5522 | 18000 | 1.5223 | 0.7460 | 0.2195 |
74
+ | 0.3219 | 94.5274 | 19000 | 1.5370 | 0.7392 | 0.2162 |
75
+ | 0.3144 | 99.5025 | 20000 | 1.5326 | 0.7415 | 0.2170 |
76
 
77
 
78
  ### Framework versions
79
 
80
  - Transformers 4.51.3
81
+ - Pytorch 2.3.0+cu118
82
  - Datasets 4.0.0
83
  - Tokenizers 0.21.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64f4b2c883e510294e6dcc23ab7bc2df23083a87819913f6b7a702a407853de9
3
  size 1262205180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f2720f10035ae6b5d26c97be9e232aff19fff68b1c709448957e62072647ced
3
  size 1262205180
runs/Jul20_18-36-31_cs-01k0mh641vxyz3b3yz4ymxh86p/events.out.tfevents.1753036864.cs-01k0mh641vxyz3b3yz4ymxh86p.8010.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cba87ebd09a2d598db257f019fcf8b3b96a52cbab85b681f662dff2623c27265
3
- size 17305
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d97078a0d32ec35e9487d42588d8b5c1d78887198caf5d4448e717b4b17c072
3
+ size 18252