whisper-hakka-t1 / README.md
ouob's picture
End of training
1d81fb5
metadata
language:
  - hi
license: apache-2.0
base_model: openai/whisper-base
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: Whisper base Hi - Sanchit Gandhi
    results: []

Whisper base Hi - Sanchit Gandhi

This model is a fine-tuned version of openai/whisper-base on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1381
  • Cer: 8.5165

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000

Training results

Training Loss Epoch Step Validation Loss Cer
0.3106 0.87 1000 0.3352 16.9784
0.1609 1.74 2000 0.1887 10.5303
0.0889 2.6 3000 0.1510 9.2926
0.0596 3.47 4000 0.1381 8.5165

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3