metadata
base_model: casual/whisper_tiny_24til
tags:
- generated_from_trainer
model-index:
- name: whisper_tiny_24til
results: []
whisper_tiny_24til
This model is a fine-tuned version of casual/whisper_tiny_24til on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.0000
- eval_wer: 2.6755
- eval_runtime: 782.4199
- eval_samples_per_second: 4.473
- eval_steps_per_second: 0.56
- epoch: 6.8493
- step: 1500
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: 10
- training_steps: 4000
Framework versions
- Transformers 4.40.2
- Pytorch 2.0.1+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1