metadata

library_name: transformers
language:
  - np
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - amitpant7/nepali-speech-to-text
metrics:
  - wer
model-index:
  - name: Whisper Small Nepali
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Nepali Speech-to-Text Dataset
          type: amitpant7/nepali-speech-to-text
          args: 'config: np, split: train'
        metrics:
          - name: Wer
            type: wer
            value: 41.82573545924096

Whisper Small Nepali

This model is a fine-tuned version of openai/whisper-small on the Nepali Speech-to-Text Dataset dataset. It achieves the following results on the evaluation set:

Loss: 0.4741
Wer: 41.8257

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 OptimizerNames.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: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0121	9.6154	1000	0.3463	44.6216
0.0014	19.2308	2000	0.4206	42.2300
0.0001	28.8462	3000	0.4535	41.8706
0.0	38.4615	4000	0.4684	41.8482
0.0	48.0769	5000	0.4741	41.8257

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.1
Tokenizers 0.21.0