metadata
library_name: transformers
license: apache-2.0
base_model: alexachang/whisper-small-csclean
tags:
- generated_from_trainer
model-index:
- name: csclean-tat
results: []
csclean-tat
This model is a fine-tuned version of alexachang/whisper-small-csclean on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.2923
- eval_cer: 12.2014
- eval_runtime: 363.1582
- eval_samples_per_second: 4.973
- eval_steps_per_second: 0.622
- epoch: 2.9118
- step: 3500
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- training_steps: 3500
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.52.4
- Pytorch 2.1.0+cu118
- Datasets 3.6.0
- Tokenizers 0.21.4