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
7ced485
·
verified ·
1 Parent(s): 8975d5d

End of training

Browse files
Files changed (2) hide show
  1. README.md +12 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 0.3886613494287562
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: 0.6916
36
- - Wer: 0.3887
37
- - Phoneme Cer: 0.1718
38
 
39
  ## Model description
40
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer | Phoneme Cer |
68
  |:-------------:|:------:|:----:|:---------------:|:------:|:-----------:|
69
- | 4.1459 | 0.2312 | 200 | 4.1380 | 1.0 | 1.0 |
70
- | 4.0546 | 0.4624 | 400 | 4.0311 | 1.0 | 1.0 |
71
- | 2.4273 | 0.6936 | 600 | 2.1457 | 0.8099 | 0.3857 |
72
- | 1.1968 | 0.9249 | 800 | 1.1103 | 0.5042 | 0.2163 |
73
- | 0.6783 | 1.1561 | 1000 | 0.8584 | 0.4265 | 0.1868 |
74
- | 0.8966 | 1.3873 | 1200 | 0.7554 | 0.4010 | 0.1781 |
75
- | 0.5504 | 1.6185 | 1400 | 0.7147 | 0.3942 | 0.1748 |
76
- | 0.64 | 1.8497 | 1600 | 0.6916 | 0.3887 | 0.1718 |
77
 
78
 
79
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 0.3384350075447295
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: 0.5343
36
+ - Wer: 0.3384
37
+ - Phoneme Cer: 0.1545
38
 
39
  ## Model description
40
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Wer | Phoneme Cer |
68
  |:-------------:|:------:|:----:|:---------------:|:------:|:-----------:|
69
+ | 0.458 | 0.2312 | 200 | 0.6372 | 0.3657 | 0.1651 |
70
+ | 0.3523 | 0.4624 | 400 | 0.6086 | 0.3552 | 0.1613 |
71
+ | 0.2547 | 0.6936 | 600 | 0.5896 | 0.3466 | 0.1581 |
72
+ | 0.2305 | 0.9249 | 800 | 0.5750 | 0.3450 | 0.1578 |
73
+ | 0.1565 | 1.1561 | 1000 | 0.5597 | 0.3405 | 0.1563 |
74
+ | 0.3241 | 1.3873 | 1200 | 0.5558 | 0.3393 | 0.1555 |
75
+ | 0.2219 | 1.6185 | 1400 | 0.5439 | 0.3399 | 0.1553 |
76
+ | 0.2741 | 1.8497 | 1600 | 0.5343 | 0.3384 | 0.1545 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a868676f208e9a348b37d9a85d03b3e46a18b35c759bb4676b2fa6a4b4b07a7f
3
  size 1262914496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e43208a1f7f2337ff46ac420c68c380e26684e4e1187e0da48ec7ae655868f8
3
  size 1262914496