whisper fine tuning
Collection
Modelau Whisper wedi eu mireinio gyda gwahanol gasgliadau o ddata, ynghyd â chanlyniadau profi.
•
12 items
•
Updated
whisper-large-v3-ft-btb-cy
This model is a fine-tuned version of openai/whisper-large-v3 on the DewiBrynJones/banc-trawsgrifiadau-bangor-clean train 2410 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4687
- Wer: 0.2887
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4429 | 0.8580 | 1000 | 0.4673 | 0.3495 |
| 0.3192 | 1.7160 | 2000 | 0.4116 | 0.2986 |
| 0.1917 | 2.5740 | 3000 | 0.4086 | 0.2937 |
| 0.1113 | 3.4320 | 4000 | 0.4341 | 0.2852 |
| 0.0665 | 4.2900 | 5000 | 0.4687 | 0.2887 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 28
Model tree for DewiBrynJones/whisper-large-v3-ft-btb-cy
Base model
openai/whisper-large-v3