Hugging Face's logo

Samuael
/
asr-alffamharic-phoneme-based

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
Samuael commited on
Commit
dae8817
·
1 Parent(s): 6cd722c

End of training

Browse files
Files changed (3) hide show
  1. README.md +7 -11
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Samuael/asr-alffamharic-phoneme-based](https://huggingface.co/Samuael/asr-alffamharic-phoneme-based) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3433
21
- - Wer: 0.4605
22
 
23
  ## Model description
24
 
@@ -38,25 +38,21 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.05
41
- - train_batch_size: 32
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
- - num_epochs: 2
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
- | 0.2414 | 0.26 | 40 | 0.3426 | 0.4608 |
54
- | 0.2901 | 0.52 | 80 | 0.3423 | 0.4605 |
55
- | 0.314 | 0.78 | 120 | 0.3418 | 0.4605 |
56
- | 0.2676 | 1.05 | 160 | 0.3417 | 0.4603 |
57
- | 0.2692 | 1.31 | 200 | 0.3413 | 0.4605 |
58
- | 0.2331 | 1.57 | 240 | 0.3420 | 0.4627 |
59
- | 0.2768 | 1.83 | 280 | 0.3433 | 0.4605 |
60
 
61
 
62
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Samuael/asr-alffamharic-phoneme-based](https://huggingface.co/Samuael/asr-alffamharic-phoneme-based) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3420
21
+ - Wer: 0.4614
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.05
41
+ - train_batch_size: 64
42
  - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 1000
47
+ - num_epochs: 1
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Wer |
52
  |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.2647 | 0.26 | 40 | 0.3420 | 0.4607 |
54
+ | 0.2841 | 0.52 | 80 | 0.3420 | 0.4603 |
55
+ | 0.2698 | 0.78 | 120 | 0.3420 | 0.4614 |
 
 
 
 
56
 
57
 
58
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c3e7151455a259705b4805e8f36e75174caa0973960270cf2812bec04aaa473
3
  size 377686878
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bffed5b6f343bdc52af2b50e4b057b10950ce4293ba29a174dfbf0d05d7e71
3
  size 377686878
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b6eb06c9f42c15cb48ca8b421eb2ad46a64ee16674f7cdaa4322738dedf6ac0
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cff90c35cc6bd331f70b407ab593e64509b7eb3f2926db4adfafbcf4609454b
3
  size 4600