Whisper Small Da - HollowVoice
This model is a fine-tuned version of openai/openai/whisper-small on the audiofolder dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.4597
- eval_wer: 22.9176
- eval_runtime: 248.1301
- eval_samples_per_second: 3.514
- eval_steps_per_second: 0.439
- epoch: 9.17
- step: 2000
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.2
- Downloads last month
- 7