Hugging Face's logo

shaunliu82714
/
whisper-small-en-genshin

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-en-genshin / README.md
shaunliu82714's picture
shaunliu82714
End of training
94de032 verified
preview code
|
raw
history blame
1.66 kB
metadata
library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small ZXL
    results: []

Whisper Small ZXL

This model is a fine-tuned version of openai/whisper-small on the GS_EN dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1531
  • Wer: 10.0178

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: 32
  • 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: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.2059 0.25 1000 0.1928 11.6620
0.1843 0.5 2000 0.1763 10.9737
0.1727 0.75 3000 0.1699 10.5659
0.1641 1.0962 4000 0.1531 10.0178

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.0