whisper-tiny-ta / README.md
parambharat's picture
update model card README.md
3410369
|
raw
history blame
1.41 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - tamil_asr_corpus
model-index:
  - name: whisper-tiny-ta
    results: []

whisper-tiny-ta

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

  • eval_loss: 0.3112
  • eval_wer: 30.1832
  • eval_runtime: 3154.5468
  • eval_samples_per_second: 3.743
  • eval_steps_per_second: 0.234
  • epoch: 0.4
  • step: 9000

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: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 1000
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2