Hugging Face's logo

Samuael
/
ethiopic-asr-characters

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Samuael commited on
Commit
34806ea
·
verified ·
1 Parent(s): d038829

End of training

Browse files
Files changed (3) hide show
  1. README.md +22 -26
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.3037292519939642
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,9 +32,9 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [Samuael/ethiopic-asr-characters](https://huggingface.co/Samuael/ethiopic-asr-characters) on the alffa_amharic dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4233
36
- - Wer: 0.3037
37
- - Phoneme Cer: 0.1439
38
 
39
  ## Model description
40
 
@@ -60,33 +60,29 @@ The following hyperparameters were used during training:
60
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 100
63
- - num_epochs: 5
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer | Phoneme Cer |
68
  |:-------------:|:------:|:----:|:---------------:|:------:|:-----------:|
69
- | 0.1902 | 0.2312 | 200 | 0.5678 | 0.3431 | 0.1555 |
70
- | 0.1622 | 0.4624 | 400 | 0.5520 | 0.3321 | 0.1532 |
71
- | 0.0933 | 0.6936 | 600 | 0.5467 | 0.3292 | 0.1527 |
72
- | 0.1337 | 0.9249 | 800 | 0.5601 | 0.3315 | 0.1531 |
73
- | 0.091 | 1.1561 | 1000 | 0.5508 | 0.3307 | 0.1522 |
74
- | 0.2286 | 1.3873 | 1200 | 0.5274 | 0.3267 | 0.1510 |
75
- | 0.1596 | 1.6185 | 1400 | 0.5085 | 0.3273 | 0.1506 |
76
- | 0.2091 | 1.8497 | 1600 | 0.4826 | 0.3198 | 0.1498 |
77
- | 0.2798 | 2.0809 | 1800 | 0.4731 | 0.3187 | 0.1489 |
78
- | 0.2678 | 2.3121 | 2000 | 0.4700 | 0.3165 | 0.1482 |
79
- | 0.2777 | 2.5434 | 2200 | 0.4521 | 0.3137 | 0.1468 |
80
- | 0.5036 | 2.7746 | 2400 | 0.4592 | 0.3133 | 0.1463 |
81
- | 0.3513 | 3.0058 | 2600 | 0.4535 | 0.3119 | 0.1469 |
82
- | 0.6127 | 3.2370 | 2800 | 0.4434 | 0.3080 | 0.1457 |
83
- | 0.3057 | 3.4682 | 3000 | 0.4377 | 0.3090 | 0.1454 |
84
- | 0.346 | 3.6994 | 3200 | 0.4348 | 0.3077 | 0.1449 |
85
- | 0.3782 | 3.9306 | 3400 | 0.4273 | 0.3035 | 0.1442 |
86
- | 0.2468 | 4.1618 | 3600 | 0.4270 | 0.3051 | 0.1442 |
87
- | 0.1932 | 4.3931 | 3800 | 0.4232 | 0.3029 | 0.1436 |
88
- | 0.3175 | 4.6243 | 4000 | 0.4269 | 0.3040 | 0.1435 |
89
- | 0.1834 | 4.8555 | 4200 | 0.4233 | 0.3037 | 0.1439 |
90
 
91
 
92
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.29963354171157575
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [Samuael/ethiopic-asr-characters](https://huggingface.co/Samuael/ethiopic-asr-characters) on the alffa_amharic dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.4428
36
+ - Wer: 0.2996
37
+ - Phoneme Cer: 0.1421
38
 
39
  ## Model description
40
 
 
60
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_steps: 100
63
+ - num_epochs: 4
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer | Phoneme Cer |
68
  |:-------------:|:------:|:----:|:---------------:|:------:|:-----------:|
69
+ | 0.1559 | 0.2312 | 200 | 0.5540 | 0.3212 | 0.1475 |
70
+ | 0.1228 | 0.4624 | 400 | 0.5394 | 0.3142 | 0.1466 |
71
+ | 0.069 | 0.6936 | 600 | 0.5525 | 0.3139 | 0.1466 |
72
+ | 0.0997 | 0.9249 | 800 | 0.5531 | 0.3118 | 0.1462 |
73
+ | 0.0732 | 1.1561 | 1000 | 0.5644 | 0.3196 | 0.1465 |
74
+ | 0.1637 | 1.3873 | 1200 | 0.5367 | 0.3185 | 0.1468 |
75
+ | 0.1145 | 1.6185 | 1400 | 0.5215 | 0.3180 | 0.1468 |
76
+ | 0.1499 | 1.8497 | 1600 | 0.4985 | 0.3141 | 0.1455 |
77
+ | 0.1975 | 2.0809 | 1800 | 0.4814 | 0.3114 | 0.1446 |
78
+ | 0.2116 | 2.3121 | 2000 | 0.4855 | 0.3085 | 0.1446 |
79
+ | 0.2384 | 2.5434 | 2200 | 0.4702 | 0.3083 | 0.1441 |
80
+ | 0.4346 | 2.7746 | 2400 | 0.4762 | 0.3063 | 0.1435 |
81
+ | 0.3156 | 3.0058 | 2600 | 0.4677 | 0.3044 | 0.1432 |
82
+ | 0.5558 | 3.2370 | 2800 | 0.4574 | 0.2993 | 0.1425 |
83
+ | 0.2787 | 3.4682 | 3000 | 0.4478 | 0.2989 | 0.1420 |
84
+ | 0.3268 | 3.6994 | 3200 | 0.4466 | 0.2978 | 0.1418 |
85
+ | 0.3461 | 3.9306 | 3400 | 0.4428 | 0.2996 | 0.1421 |
 
 
 
 
86
 
87
 
88
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:778e33fbe3f077506d772c6bf0ae7ec0537be437f1b6ee296a1e5bd156c481ac
3
  size 1262914496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd638d5589022af19ef15af6ad0691e159167cc966165af5da197e7c4db3894c
3
  size 1262914496
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464f3f6960b0e2a8868b906119913e2bc11aab64c006a64d2faecd4a1e0bd905
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5cb5785a2b15e3aed6d250388d88caa8581e6a6063e15b0be5571c350f93989
3
  size 5240