---
base_model: openai/whisper-tiny

datasets:

  • local_data language: fr metrics:

  • wer

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

    This model was created from the Mozilla.ai Blueprint: speech-to-text-finetune.

    Evaluation results on 2 audio samples of French

    Baseline model (before finetuning) on French

    • Word Error Rate: 75.0
    • Loss: 2.516

    Finetuned model (after finetuning) on French

    • Word Error Rate: 75.0
    • Loss: 2.499
Downloads last month
18
Safetensors
Model size
37.8M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.