Hugging Face's logo

Pageee
/
DistilFT-Frisian-10ha

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Western Frisian
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
DistilFT-Frisian-10ha / README.md
Pageee's picture
Pageee
End of training
b819feb verified
preview code
|
raw
history blame contribute delete
1.41 kB
metadata
language:
  - fy
base_model: distil-small.en
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_6_1
model-index:
  - name: DistilFT-Frisian-10h
    results: []

DistilFT-Frisian-10h

This model is a fine-tuned version of distil-small.en on the mozilla-foundation/common_voice_6_fy_NL dataset. It achieves the following results on the evaluation set:

  • eval_loss: 1.3027
  • eval_wer: 61.4400
  • eval_runtime: 570.9376
  • eval_samples_per_second: 5.29
  • eval_steps_per_second: 0.662
  • epoch: 4.8128
  • step: 4500

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-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: 250
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1