Hugging Face's logo

seyyaw
/
whisper-finetuned-amharic

Automatic Speech Recognition
Transformers
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Community
seyyaw commited on
Commit
93c1691
·
verified ·
1 Parent(s): 8ef98f0

End of training

Browse files
Files changed (3) hide show
  1. README.md +6 -15
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.5902
22
- - Wer: 2.7316
23
- - Cer: 3.0021
24
 
25
  ## Model description
26
 
@@ -40,8 +40,8 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
- - train_batch_size: 2
44
- - eval_batch_size: 4
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
@@ -52,16 +52,7 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
55
- | 2.0672 | 0.1 | 20 | 1.9614 | 1.0866 | 2.5477 |
56
- | 1.8145 | 0.2 | 40 | 1.8406 | 1.0157 | 2.5646 |
57
- | 1.8231 | 0.3 | 60 | 1.7589 | 2.3898 | 2.7175 |
58
- | 1.7399 | 0.4 | 80 | 1.7080 | 2.2848 | 2.6377 |
59
- | 1.6576 | 0.5 | 100 | 1.6876 | 1.8097 | 2.5961 |
60
- | 1.6655 | 0.6 | 120 | 1.6609 | 3.3871 | 3.1712 |
61
- | 1.6613 | 0.7 | 140 | 1.6364 | 2.8038 | 3.0409 |
62
- | 1.6039 | 0.8 | 160 | 1.6145 | 1.25 | 2.6169 |
63
- | 1.5773 | 0.9 | 180 | 1.6039 | 1.2421 | 2.6039 |
64
- | 1.5844 | 1.0 | 200 | 1.5902 | 2.7316 | 3.0021 |
65
 
66
 
67
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.9679
22
+ - Wer: 2.0538
23
+ - Cer: 2.8758
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
55
+ | 1.9752 | 1.0 | 20 | 1.9679 | 3.7220 | 4.7877 |
 
 
 
 
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:280e96f936ba422ec33a7ddd4aa05aa7ffeafada592e23fbc803c7ccb0ada367
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9adfb60f396a958175e5e9485c30c30fdbd728f27903282247d9463d57aa9cf5
3
  size 966995080
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e50aeff4bd5de4ad2b71540317fcb4187409ad02c5fe4884b78866f561025c4e
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab94405ce33dcf6b1b8c1f7a4507bd8a174c22dcf301786aeaef27b11c7646a6
3
  size 5432