README.md

metadata

language:
  - lv
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper medium LV - Felikss Kleins
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: lv
          split: None
          args: 'config: lv, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 50

Whisper medium LV - Felikss Kleins

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.9473
• Wer: 50.0

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	399.0	200	0.9567	57.6923
0.3396	799.0	400	0.9473	50.0

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2