Hugging Face's logo

FunPang
/
whisper-small-Cantonese-fine-tune

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
FunPang commited on
Commit
1a96ebd
•
1 Parent(s): 0ad1fcb

FunPang/whisper-small-Cantonese-fine-tunet-200

Browse files
Files changed (4) hide show
  1. README.md +10 -9
  2. model.safetensors +1 -1
  3. runs/Sep25_20-19-47_asus2/events.out.tfevents.1727320789.asus2.45408.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,11 +1,11 @@
1
  ---
2
- base_model: openai/whisper-small
3
  library_name: transformers
4
  license: apache-2.0
5
- metrics:
6
- - wer
7
  tags:
8
  - generated_from_trainer
 
 
9
  model-index:
10
  - name: whisper-small-Cantonese-fine-tune
11
  results: []
@@ -18,8 +18,8 @@ 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: 0.1843
22
- - Wer: 87.5
23
 
24
  ## Model description
25
 
@@ -45,14 +45,15 @@ 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: 5
48
- - training_steps: 100
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Wer |
54
- |:-------------:|:-----:|:----:|:---------------:|:----:|
55
- | 0.0003 | 25.0 | 100 | 0.1843 | 87.5 |
 
56
 
57
 
58
  ### Framework versions
 
1
  ---
 
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: openai/whisper-small
 
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: whisper-small-Cantonese-fine-tune
11
  results: []
 
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: 0.2105
22
+ - Wer: 100.0
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 5
48
+ - training_steps: 200
49
  - mixed_precision_training: Native AMP
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:-----:|
55
+ | 0.0001 | 25.0 | 100 | 0.2022 | 112.5 |
56
+ | 0.0001 | 50.0 | 200 | 0.2105 | 100.0 |
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12161be2833e336398c9d7fa58412315935628dd9025da824debf97b44d3d4b1
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425afd8654882ac6dbc946965315bfc926148c23e03943376bca45d0a6da45aa
3
  size 966995080
runs/Sep25_20-19-47_asus2/events.out.tfevents.1727320789.asus2.45408.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e39822d52963a7f7730b43025e0b78a409a553a0f24ec1d9c6bd3a6d95c737
3
+ size 8521
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54804d82a843a054ccfe51359044eb4c4d7f27615d9d24cb3a0770b5e9b646fb
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbb4512a65162a1eb2b23e0798600949f0413ee290cdceba3c7f5c341f3a7fe
3
  size 5432