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 10h
    results: []

Whisper Small Frisian 10h

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: 0.3577
eval_wer: 23.2329
eval_runtime: 599.1927
eval_samples_per_second: 5.04
eval_steps_per_second: 0.631
epoch: 1.0695
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: 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: 2000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.40.1
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.19.1