Downloads · 30 days
7
16% of all-time downloads
whisper-small-ko-Y-SA
Gummybear05/whisper-small-ko-Y-SA
whisper-small-ko-Y-SA is a automatic speech recognition model from Gummybear05. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
45
Public
Parameters
242M
30 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Dec 20, 2023
- Updated
- Dec 20, 2023
- SHA
- 49ec082b
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
whisper-small-ko-Y-SA
This model is a fine-tuned version of openai/whisper-small on the aihub adult speed changed dataset. It achieves the following results on the evaluation set:
- Loss: 0.3020
- Cer: 8.4704
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.228 | 0.13 | 100 | 0.3171 | 8.3647 |
| 0.198 | 0.26 | 200 | 0.3088 | 8.6055 |
| 0.1598 | 0.39 | 300 | 0.3301 | 9.3104 |
| 0.1629 | 0.52 | 400 | 0.2979 | 8.1062 |
| 0.1498 | 0.64 | 500 | 0.3000 | 7.8712 |
| 0.128 | 0.77 | 600 | 0.3037 | 7.9770 |
| 0.1291 | 0.9 | 700 | 0.3018 | 7.9124 |
| 0.0707 | 1.03 | 800 | 0.2978 | 7.8301 |
| 0.0595 | 1.16 | 900 | 0.3017 | 7.6128 |
| 0.0655 | 1.29 | 1000 | 0.3085 | 8.1708 |
| 0.056 | 1.42 | 1100 | 0.3127 | 7.7714 |
| 0.0615 | 1.55 | 1200 | 0.2992 | 8.8698 |
| 0.0562 | 1.68 | 1300 | 0.3026 | 8.1826 |
| 0.0574 | 1.81 | 1400 | 0.3212 | 8.5703 |
| 0.0591 | 1.93 | 1500 | 0.3096 | 8.1297 |
| 0.0353 | 2.06 | 1600 | 0.3072 | 8.8170 |
| 0.0331 | 2.19 | 1700 | 0.3009 | 8.2413 |
| 0.0259 | 2.32 | 1800 | 0.3043 | 7.7009 |
| 0.0293 | 2.45 | 1900 | 0.3093 | 8.5468 |
| 0.0305 | 2.58 | 2000 | 0.3066 | 11.0374 |
| 0.028 | 2.71 | 2100 | 0.2957 | 9.6393 |
| 0.0333 | 2.84 | 2200 | 0.2964 | 9.6511 |
| 0.0301 | 2.97 | 2300 | 0.3006 | 7.8184 |
| 0.0171 | 3.09 | 2400 | 0.3011 | 8.1532 |
| 0.0151 | 3.22 | 2500 | 0.3062 | 8.0886 |
| 0.0163 | 3.35 | 2600 | 0.3065 | 8.5761 |
| 0.0218 | 3.48 | 2700 | 0.3019 | 7.7773 |
| 0.023 | 3.61 | 2800 | 0.3022 | 8.1943 |
| 0.0144 | 3.74 | 2900 | 0.3021 | 9.2281 |
| 0.0164 | 3.87 | 3000 | 0.3024 | 8.5350 |
| 0.0211 | 4.0 | 3100 | 0.3020 | 8.4704 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- hi
- Created
- Dec 20, 2023
- Updated
- Dec 20, 2023