Hugging Face's logo

melvinrajendran
/
whisper-tiny-coraal

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
whisper-tiny-coraal / README.md
melvinrajendran's picture
melvinrajendran
End of training
8544e9d verified
preview code
|
raw
history blame contribute delete
1.53 kB
metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - DynamicSuperb/AAVESpeechRecognition_CORAAL
model-index:
  - name: Whisper Tiny - CORAAL
    results: []

Whisper Tiny - CORAAL

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

  • eval_loss: 1.3805
  • eval_model_preparation_time: 0.0026
  • eval_wer: 44.7790
  • eval_runtime: 24.5707
  • eval_samples_per_second: 3.256
  • eval_steps_per_second: 0.407
  • step: 0

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

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.21.0