README.md

metadata

language:
  - lt
license: apache-2.0
tags:
  - lt-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small LT - Lithuanian Whisper
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: lt
          split: train+validation
          args: lt
        metrics:
          - name: Wer
            type: wer
            value: 32.65614439629468

Whisper Small LT - Lithuanian Whisper

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

• Loss: 0.3871
• Wer: 32.6561

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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2419	1.8	1000	0.3749	38.7707
0.0425	3.6	2000	0.3591	34.2345
0.0062	5.4	3000	0.3779	32.7555
0.0034	7.19	4000	0.3871	32.6561

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.6.1
• Tokenizers 0.13.2