metadata

license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
metrics:
  - wer
model-index:
  - name: whisper-tiny-finetune-hindi-fleurs
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: hi_in
          split: train
          args: hi_in
        metrics:
          - name: Wer
            type: wer
            value: 0.8889948502765592

whisper-tiny-finetune-hindi-fleurs

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

Loss: 0.8973
Wer Ortho: 0.8687
Wer: 0.8890

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
1.9951	0.83	100	1.8632	1.1021	1.1432
1.2634	1.67	200	1.2561	1.0496	1.1282
0.8868	2.5	300	1.0672	0.8591	0.8911
0.6568	3.33	400	0.9656	0.9689	1.0460
0.5288	4.17	500	0.8973	0.8687	0.8890

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.0
Tokenizers 0.15.0