metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_6_1
model-index:
- name: Whisper Small Frisian 1h
results: []
Whisper Small Frisian 1h
This model is a fine-tuned version of openai/whisper-small on the Common Voice 6.1 dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.9050
- eval_wer: 43.8389
- eval_runtime: 596.14
- eval_samples_per_second: 5.066
- eval_steps_per_second: 0.634
- epoch: 7.8652
- step: 700
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: 3e-06
- train_batch_size: 8
- 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: 50
- training_steps: 1500
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.40.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1