Hugging Face's logo

5roop
/
output

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Croatian
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
5roop commited on
Commit
5919e0d
•
1 Parent(s): b39289f

End of training

Browse files
Files changed (5) hide show
  1. README.md +16 -8
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
  4. runs/Mar18_18-27-02_kt-gpu2/events.out.tfevents.1710782824.kt-gpu2.614918.0 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Mići Princ dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 1.1816
23
- - Wer: 36.2647
24
 
25
  ## Model description
26
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 7e-06
43
  - train_batch_size: 4
44
  - eval_batch_size: 8
45
  - seed: 42
@@ -48,15 +48,23 @@ The following hyperparameters were used during training:
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 100
51
- - training_steps: 618
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Wer |
57
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
58
- | 0.0014 | 17.66 | 309 | 1.1196 | 29.9832 |
59
- | 0.0007 | 35.31 | 618 | 1.1816 | 36.2647 |
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Mići Princ dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 1.4596
23
+ - Wer: 33.5008
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
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
 
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_steps: 100
51
+ - training_steps: 3090
52
  - mixed_precision_training: Native AMP
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
57
+ |:-------------:|:------:|:----:|:---------------:|:-------:|
58
+ | 0.0013 | 17.66 | 309 | 1.1495 | 37.1859 |
59
+ | 0.0009 | 35.31 | 618 | 1.1700 | 27.3032 |
60
+ | 0.0001 | 52.97 | 927 | 1.3428 | 27.7219 |
61
+ | 0.0001 | 70.63 | 1236 | 1.3874 | 27.2194 |
62
+ | 0.0001 | 88.29 | 1545 | 1.4141 | 27.3869 |
63
+ | 0.0001 | 105.94 | 1854 | 1.4331 | 33.5008 |
64
+ | 0.0001 | 123.6 | 2163 | 1.4445 | 33.3333 |
65
+ | 0.0 | 141.26 | 2472 | 1.4520 | 33.3333 |
66
+ | 0.0 | 158.91 | 2781 | 1.4576 | 33.3333 |
67
+ | 0.0 | 176.57 | 3090 | 1.4596 | 33.5008 |
68
 
69
 
70
  ### Framework versions
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90c260c825d6974da993d6f8fc8f9644922259d82788d7eb999fe63639732e83
3
  size 4993448880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9d0a07c46f6aaea869908135d7265d1a1c9e9cdbaaf396ddb58f476176488f
3
  size 4993448880
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d47c5b5c4ff177d275879f3dedd654495f8e42654e3f5bd39c4641cc9722b315
3
  size 1180663192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3ce37ef94af489a9ab165b9eab291a07e1f362c32ca4c71cb2040e567c2b29
3
  size 1180663192
runs/Mar18_18-27-02_kt-gpu2/events.out.tfevents.1710782824.kt-gpu2.614918.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40eb496c90d62d83c43235e46a91a2e882bf0b7a447858f650936f5ae84d6e0
3
+ size 34834
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ade9d52e81c11df3ded7c0b2ba6e191f585955e2b34074980f57fe216763274
3
  size 4539
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7c8afe35a9920337dea36688dd654ef483d047a5d808a5092c503e7f9e094e
3
  size 4539