<!-- 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-tiny-testing-common-voice
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.1334
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: 0.0015
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- distributed_type: tpu
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3885 | 14.29 | 100 | 3.7435 |
| 1.1828 | 28.57 | 200 | 3.7666 |
| 0.773 | 42.86 | 300 | 3.8743 |
| 0.5042 | 57.14 | 400 | 3.9884 |
| 0.3311 | 71.43 | 500 | 4.0333 |
| 0.2123 | 85.71 | 600 | 4.4089 |
| 0.1247 | 100.0 | 700 | 4.5347 |
| 0.0659 | 114.29 | 800 | 4.7366 |
| 0.0257 | 128.57 | 900 | 5.0738 |
| 0.0069 | 142.86 | 1000 | 5.1334 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.1.0a0+gitcc01568
- Datasets 2.12.0
- Tokenizers 0.13.3
