---
{}
---

    ---
    base_model: openai/whisper-tiny
datasets:
- local_data/custom_2
language: el
metrics:
- wer
    ---

    # Finetuned version of openai/whisper-tiny on 8 Greek training audio samples from local_data/custom_2.

    This model was created from the Mozilla.ai Blueprint:
    [speech-to-text-finetune](https://github.com/mozilla-ai/speech-to-text-finetune).

    ## Evaluation results on 2 audio samples of Greek

    ### Baseline model (before finetuning) on Greek
    - Word Error Rate: 84.615
    - Loss: 1.706

    ### Finetuned model (after finetuning) on Greek
    - Word Error Rate: 84.615
    - Loss: 1.097