Raydox10's picture
End of training
39b2dfc verified
metadata
library_name: transformers
language:
  - tw
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - fsicoli/common_voice_18_0
metrics:
  - wer
model-index:
  - name: Raydox11-whisper-small
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: fsicoli/common_voice_18_0
          type: fsicoli/common_voice_18_0
          config: tw
          split: None
          args: 'config: tw, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 85.39325842696628

Raydox11-whisper-small

This model is a fine-tuned version of openai/whisper-small on the fsicoli/common_voice_18_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.7598
  • Wer: 85.3933

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: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 5
  • total_train_batch_size: 20
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 700
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0003 83.3333 700 1.7598 85.3933

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1