Hugging Face's logo

yuweiiizz
/
whisper-small-taiwanese

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Min Nan Chinese
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
yuweiiizz commited on
Commit
6b391dc
·
verified ·
1 Parent(s): 01c34fc

End of training

Browse files
Files changed (4) hide show
  1. README.md +10 -8
  2. model.safetensors +1 -1
  3. runs/May02_20-37-01_e28a9477d34f/events.out.tfevents.1714682245.e28a9477d34f.26.0 +3 -0
  4. 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-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6474
23
  - Cer: 48.6382
 
24
 
25
  ## Model description
26
 
@@ -40,9 +40,11 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
- - train_batch_size: 16
44
  - eval_batch_size: 8
45
  - seed: 42
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
@@ -50,12 +52,12 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Cer |
54
- |:-------------:|:------:|:----:|:---------------:|:-------:|
55
- | 0.9789 | 0.6452 | 1000 | 0.9021 | 60.2169 |
56
- | 0.61 | 1.2903 | 2000 | 0.7536 | 53.3884 |
57
- | 0.5611 | 1.9355 | 3000 | 0.6703 | 51.3360 |
58
- | 0.3359 | 2.5806 | 4000 | 0.6474 | 48.6382 |
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 Common Voice 16.1 dataset.
21
  It achieves the following results on the evaluation set:
 
22
  - Cer: 48.6382
23
+ - Loss: 0.6474
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 1e-05
43
+ - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
46
+ - gradient_accumulation_steps: 2
47
+ - total_train_batch_size: 16
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - lr_scheduler_warmup_ratio: 0.1
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Cer | Validation Loss |
56
+ |:-------------:|:------:|:----:|:-------:|:---------------:|
57
+ | 0.9789 | 0.6452 | 1000 | 60.2169 | 0.9021 |
58
+ | 0.61 | 1.2903 | 2000 | 53.3884 | 0.7536 |
59
+ | 0.5611 | 1.9355 | 3000 | 51.3360 | 0.6703 |
60
+ | 0.3359 | 2.5806 | 4000 | 48.6382 | 0.6474 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b35281e57f38653ec64c5bc5be60610b3bddf528283e52b17f94b101f0da1e3
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bfea1f8ccff1d3d104539ef9c86c38d6670980c839e6047b65be8f2eae783c8
3
  size 966995080
runs/May02_20-37-01_e28a9477d34f/events.out.tfevents.1714682245.e28a9477d34f.26.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:233f02ac0206f4640335f4f7bcda1b6ac4048b862b3b6a44f8c8dfffa82cdc63
3
+ size 5874
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc814e8346759fc832d3d40fb2efbd9f7f5bf91489499603abb8463206368d6b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4aa089c8d20ef1e6682de99276d895d292be75b8461ac76dc70d3b16c323a0
3
  size 5176