Hugging Face's logo

stevehoang9
/
whisper-small2-vi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stevehoang9 commited on
Commit
3db4cec
•
1 Parent(s): 6595533

duylong/finetuneWhisper

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/Jul31_18-04-54_TUF-GAMING-Z690-PLUS-D4/events.out.tfevents.1722423896.TUF-GAMING-Z690-PLUS-D4.370156.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [vinai/PhoWhisper-small](https://huggingface.co/vinai/PhoWhisper-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 4.3932
20
- - Wer: 14.7083
21
 
22
  ## Model description
23
 
@@ -45,18 +45,18 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
- - training_steps: 50
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
55
- | 4.4978 | 0.016 | 10 | 6.7262 | 14.7083 |
56
- | 4.2997 | 0.032 | 20 | 6.4491 | 14.7083 |
57
- | 4.5058 | 0.048 | 30 | 6.0075 | 14.6948 |
58
- | 3.9571 | 0.064 | 40 | 5.3437 | 14.7083 |
59
- | 3.3732 | 0.08 | 50 | 4.3932 | 14.7083 |
60
 
61
 
62
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [vinai/PhoWhisper-small](https://huggingface.co/vinai/PhoWhisper-small) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2336
20
+ - Wer: 7.8066
21
 
22
  ## Model description
23
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 500
48
+ - training_steps: 5000
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
55
+ | 0.3058 | 1.6 | 1000 | 0.3433 | 28.2955 |
56
+ | 0.1055 | 3.2 | 2000 | 0.3438 | 10.0351 |
57
+ | 0.0521 | 4.8 | 3000 | 0.2550 | 7.4959 |
58
+ | 0.0073 | 6.4 | 4000 | 0.2338 | 7.8336 |
59
+ | 0.0032 | 8.0 | 5000 | 0.2336 | 7.8066 |
60
 
61
 
62
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d401c4ff4ffa8662d04f9fea7836aabfa30c5ce3ecb3a49c3645575452d8f82
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133caec5a8bc9f176510a6b06931cd6d702451c936214c50f03d4f87172a0811
3
  size 966995080
runs/Jul31_18-04-54_TUF-GAMING-Z690-PLUS-D4/events.out.tfevents.1722423896.TUF-GAMING-Z690-PLUS-D4.370156.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce74499398e3daafea4b85fa2f1f422b2e872c369eb17e7fb5bb9ee4f3d9eb7
3
+ size 218591
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9c17ef5b7e48ffec300641af481d393bee3144ed778d90928f2c175b0893e14
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd87cbef600844622ef44ab07446b1f0fccee9e6a8ad3a2113ee077ff4a5b846
3
  size 5368