metadata

library_name: transformers
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - razhan/DOLMA-speech
metrics:
  - bleu
model-index:
  - name: whisper-base-hawrami
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: razhan/DOLMA-speech hawrami
          type: razhan/DOLMA-speech
          args: hawrami
        metrics:
          - name: Bleu
            type: bleu
            value: 0.403603847823992

whisper-base-hawrami

This model is a fine-tuned version of openai/whisper-base on the razhan/DOLMA-speech hawrami dataset. It achieves the following results on the evaluation set:

Loss: 3.0851
Chrf: 13.3279
Bleu: 0.4036

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: 256
eval_batch_size: 128
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: 100
num_epochs: 4.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf	Bleu
4.056	1.0	40	3.7037	12.1151	0.0829
3.4175	2.0	80	3.2226	11.2675	0.1153
3.1704	3.0	120	3.1141	12.9709	0.2803
3.0286	4.0	160	3.0851	13.3279	0.4036

Framework versions

Transformers 4.49.0.dev0
Pytorch 2.6.0+cu124
Datasets 3.2.0
Tokenizers 0.21.0