metadata

language:
  - mn
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_0
metrics:
  - wer
base_model: openai/whisper-large-v2
model-index:
  - name: Whisper Large Mongolian
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 16.0
          type: mozilla-foundation/common_voice_16_0
          config: mn
          split: None
          args: 'config: mn, split: test'
        metrics:
          - type: wer
            value: 37.23357981731187
            name: Wer

Whisper Large Mongolian

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.4028
Wer: 37.2336

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: 4
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: 50
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3446	0.99	1000	0.4391	51.4572
0.1481	1.98	2000	0.3765	42.2412
0.076	2.97	3000	0.3830	39.0822
0.0149	3.96	4000	0.4028	37.2336

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.17.1
Tokenizers 0.15.2