metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
model-index:
- name: whisper-try1
results: []
whisper-try1
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 1.2065
- eval_wer: 0.3535
- eval_runtime: 15.3966
- eval_samples_per_second: 0.649
- eval_steps_per_second: 0.065
- epoch: 71.4286
- step: 1000
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: 1
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1