whisper-tindy-aug-29dec
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2599
- Wer: 86.0590
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.3988 | 1.0 | 382 | 1.1534 | 102.0613 |
| 0.8626 | 2.0 | 764 | 0.6005 | 103.0809 |
| 0.5328 | 3.0 | 1146 | 0.4433 | 97.7146 |
| 0.4241 | 4.0 | 1528 | 0.3774 | 95.2402 |
| 0.3659 | 5.0 | 1910 | 0.3395 | 93.0998 |
| 0.3262 | 6.0 | 2292 | 0.3133 | 92.2867 |
| 0.2979 | 7.0 | 2674 | 0.2935 | 89.7332 |
| 0.2736 | 8.0 | 3056 | 0.2797 | 89.9925 |
| 0.2562 | 9.0 | 3438 | 0.2681 | 87.9532 |
| 0.2395 | 10.0 | 3820 | 0.2599 | 86.0590 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0
- Datasets 3.2.0
- Tokenizers 0.20.3
- Downloads last month
- 173
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for PhanithLIM/whisper-tiny-aug-29dec
Base model
openai/whisper-tiny