metadata

language:
  - mn
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: 'Whisper Small MN - Ankhbayasgalan Davaadorj '
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1
          type: mozilla-foundation/common_voice_16_1
          config: mn
          split: test
          args: 'config: mn, split: test+validation'
        metrics:
          - name: Wer
            type: wer
            value: 67.84162771514984

Whisper Small MN - Ankhbayasgalan Davaadorj

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:

Loss: 0.5096
Wer: 67.8416

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 3000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0832	3.94	1000	0.3988	73.6211
0.0051	7.87	2000	0.4563	66.0654
0.0004	11.81	3000	0.5096	67.8416

Framework versions

Transformers 4.37.2
Pytorch 1.12.1+cu116
Datasets 2.17.0
Tokenizers 0.15.2