metadata

base_model: openai/whisper-large-v3
datasets:
  - google/fleurs
language:
  - fa
license: apache-2.0
metrics:
  - wer
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
model-index:
  - name: Whisper Large V3 fa ft 2 - Chee Li
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Google Fleurs
          type: google/fleurs
          config: fa_ir
          split: None
          args: 'config: fa split: test'
        metrics:
          - type: wer
            value: 24.19210053859964
            name: Wer

Whisper Large V3 fa ft 2 - Chee Li

This model is a fine-tuned version of openai/whisper-large-v3 on the Google Fleurs dataset. It achieves the following results on the evaluation set:

Loss: 0.1595
Wer: 24.1921

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-06
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 250
training_steps: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1176	2.3041	500	0.1506	14.7516
0.0718	4.6083	1000	0.1432	20.4020
0.0501	6.9124	1500	0.1535	23.5787
0.0332	9.2166	2000	0.1595	24.1921

Framework versions

Transformers 4.42.4
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1