Hugging Face's logo

YassineBenlaria
/
testing_pretrained_tamasheq_only

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Community
YassineBenlaria commited on
Commit
06a21dd
•
1 Parent(s): ee6d091

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -10
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
@@ -13,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # testing_pretrained_tamasheq_only
15
 
16
- This model was trained from scratch on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.5616
19
- - Wer: 0.8593
20
 
21
  ## Model description
22
 
@@ -44,18 +45,21 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 500
47
- - num_epochs: 250
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:------:|:----:|:---------------:|:------:|
53
- | 6.486 | 35.29 | 300 | 2.9498 | 1.0 |
54
- | 2.859 | 70.59 | 600 | 2.7420 | 1.0 |
55
- | 2.7652 | 105.88 | 900 | 2.7188 | 1.0 |
56
- | 2.6354 | 141.18 | 1200 | 2.2511 | 1.0 |
57
- | 1.9486 | 176.47 | 1500 | 1.5854 | 0.9111 |
58
- | 1.3512 | 211.76 | 1800 | 1.5616 | 0.8593 |
 
 
 
59
 
60
 
61
  ### Framework versions
 
1
  ---
2
+ base_model: YassineBenlaria/testing_pretrained_tamasheq_only
3
  tags:
4
  - generated_from_trainer
5
  metrics:
 
14
 
15
  # testing_pretrained_tamasheq_only
16
 
17
+ This model is a fine-tuned version of [YassineBenlaria/testing_pretrained_tamasheq_only](https://huggingface.co/YassineBenlaria/testing_pretrained_tamasheq_only) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.4042
20
+ - Wer: 0.8037
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
+ - num_epochs: 350
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Wer |
53
  |:-------------:|:------:|:----:|:---------------:|:------:|
54
+ | 3.6733 | 35.29 | 300 | 2.7902 | 1.0 |
55
+ | 2.3267 | 70.59 | 600 | 1.7481 | 0.8778 |
56
+ | 1.003 | 105.88 | 900 | 1.8251 | 0.8 |
57
+ | 0.6905 | 141.18 | 1200 | 2.0436 | 0.8148 |
58
+ | 0.5074 | 176.47 | 1500 | 2.1611 | 0.8259 |
59
+ | 0.3883 | 211.76 | 1800 | 2.2562 | 0.8333 |
60
+ | 0.3431 | 247.06 | 2100 | 2.3761 | 0.8148 |
61
+ | 0.3053 | 282.35 | 2400 | 2.3995 | 0.8074 |
62
+ | 0.2898 | 317.65 | 2700 | 2.4042 | 0.8037 |
63
 
64
 
65
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cee43b491499f4b5486d1bc0f92d3f02b4f77dc5bdd76fd418089c30e1bd6b5d
3
  size 377674145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024b51989f97a87f8787e736547e28388cafeb0151fd4edf90ba3da2d39dcccb
3
  size 377674145