whisper_lv2_v1
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2485
- Wer: 18.7231
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1687 | 1.0 | 48 | 1.0313 | 19.8231 |
| 0.042 | 2.0 | 96 | 1.0421 | 18.3166 |
| 0.0189 | 3.0 | 144 | 1.0886 | 18.4840 |
| 0.0125 | 4.0 | 192 | 1.1275 | 18.0057 |
| 0.0108 | 5.0 | 240 | 1.1485 | 17.7905 |
| 0.0106 | 6.0 | 288 | 1.1270 | 17.1927 |
| 0.0072 | 7.0 | 336 | 1.1054 | 16.0928 |
| 0.0076 | 8.0 | 384 | 1.1554 | 17.6471 |
| 0.0083 | 9.0 | 432 | 1.2121 | 18.1731 |
| 0.0093 | 10.0 | 480 | 1.2485 | 18.7231 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Downloads last month
- 5
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 TakuyaJimbo/whisper_lv2_v1
Base model
openai/whisper-large-v2