README.md

metadata

language:
  - mn
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Mn - akmoyu
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 42.52948885976409

Whisper Medium Mn - akmoyu

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7233
• Wer: 42.5295

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: 32
• eval_batch_size: 16
• 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0182	7.94	1000	0.5995	46.5269
0.0027	15.87	2000	0.6499	44.2169
0.0002	23.81	3000	0.7057	42.5623
0.0001	31.75	4000	0.7233	42.5295

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.6.1
• Tokenizers 0.13.2