Model Card for Model ID
Model Details
Model Description
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- Model type: ASR
- Language(s) (NLP): Breton
- Finetuned from model [optional]: ArzhurKoadek/whisper-small-br
Model Sources [optional]
- Repository: https://github.com/WassimZm/STT-Breton-language
Training Details
Training Data
- Dastum YAR Dataset https://huggingface.co/datasets/OuassimZm/Dastum-yar-stt-breton-data
Training Hyperparameters
The following hyperparameters were used during training:
- Learning rate: 0.001
- Per device Training batch size: 8
- Per device Evaluation batch size: 8
- Gradient accumulation steps: 1
- Number of epochs: 3
Evaluation
Metrics
The model was evaluated using the following metrics:
Character Error Rate (CER): Measures the percentage of characters that are incorrectly predicted.
Word Error Rate (WER): Measures the percentage of words that are incorrectly predicted, taking into account insertions, deletions, and substitutions.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support