baseWhisper_finetune
This model is a fine-tuned version of openai/whisper-base on the 1000freetalksample dataset. It achieves the following results on the evaluation set:
- Loss: 0.6588
- Cer: 15.5067
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: 8
- 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: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.0032 | 20.0 | 1000 | 0.6588 | 15.5067 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for gingercake01/STT_1000audio_basev3
Base model
openai/whisper-base