Hugging Face's logo

csb05
/
whisper-small-RESEARCH

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Tagalog
whisper
Generated from Trainer
Model card Files Metrics Community
whisper-small-RESEARCH / README.md
csb05's picture
csb05
End of training
7bfca5b verified
preview code
|
raw
history blame contribute delete
1.75 kB
metadata
library_name: transformers
language:
  - tl
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper small tl - CSB05
    results: []

whisper small tl - CSB05

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8685
  • Wer: 24.4015

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • 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
0.0158 8.9286 1000 0.6826 24.1285
0.0019 17.8571 2000 0.7977 24.7795
0.0003 26.7857 3000 0.8517 24.4645
0.0002 35.7143 4000 0.8685 24.4015

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.1