Hugging Face's logo

Sagicc
/
whisper-small-sr-jv

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Serbian
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Sagicc commited on
Commit
6a05f23
•
1 Parent(s): e821870

End of training

Browse files
Files changed (4) hide show
  1. README.md +12 -6
  2. model.safetensors +1 -1
  3. runs/Nov29_15-57-23_andrax-ml/events.out.tfevents.1701269849.andrax-ml.2084.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Juzne Vesti dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.7620
23
- - Wer Ortho: 0.4636
24
- - Wer: 0.3491
25
 
26
  ## Model description
27
 
@@ -47,15 +47,21 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 50
50
- - training_steps: 1000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
57
- | 0.6039 | 0.74 | 500 | 0.8077 | 0.4916 | 0.3782 |
58
- | 0.4721 | 1.48 | 1000 | 0.7620 | 0.4636 | 0.3491 |
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Juzne Vesti dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.8988
23
+ - Wer Ortho: 0.4591
24
+ - Wer: 0.3415
25
 
26
  ## Model description
27
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 50
50
+ - training_steps: 4000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
57
+ | 0.5956 | 0.74 | 500 | 0.8063 | 0.4794 | 0.3674 |
58
+ | 0.4401 | 1.48 | 1000 | 0.7975 | 0.4574 | 0.3423 |
59
+ | 0.3029 | 2.22 | 1500 | 0.7821 | 0.4512 | 0.3392 |
60
+ | 0.3016 | 2.96 | 2000 | 0.7828 | 0.4497 | 0.3318 |
61
+ | 0.2372 | 3.7 | 2500 | 0.8254 | 0.4503 | 0.3335 |
62
+ | 0.1762 | 4.44 | 3000 | 0.8402 | 0.4505 | 0.3381 |
63
+ | 0.1414 | 5.18 | 3500 | 0.8945 | 0.4584 | 0.3418 |
64
+ | 0.1326 | 5.92 | 4000 | 0.8988 | 0.4591 | 0.3415 |
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ab637f01fc0bec24f0f85f8194b9f1aa68702524ed4b8000ac93faada2f217
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613564b805d30dbe2859daf98dc2be049e4cad246f55934c8f8908707fda9a28
3
  size 966995080
runs/Nov29_15-57-23_andrax-ml/events.out.tfevents.1701269849.andrax-ml.2084.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41725a82f6a086cedadfa892d1bf83b3fd614f12559994aba5203dbd28dba2de
3
+ size 34417
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:621868eb25863629b77ecf6219bfc560c7be17d1be61ce0e6ed815ca201b5fc6
3
  size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705a09dd6b7cc96f3ceea5158643003f3c3ad37d0d30d994e29ed021a42ada20
3
  size 4283