ModernBERT Multiclass Disfluency Detection
This model is fine-tuned from answerdotai/ModernBERT-base for multi-class disfluency detection in spoken language.
Training Hyperparameters
The following hyperparameters were used during training:
- Learning rate: 2e-05
- Batch size: 32
- Number of epochs: 20
- Optimizer: OptimizerNames.ADAMW_8BIT
- LR scheduler type: SchedulerType.COSINE
- Warmup ratio: 0.1
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Evaluation results
- Accuracy on Disfluency Datasettest set self-reported0.953
- F1 on Disfluency Datasettest set self-reported0.903