wosota asr medium v1 This model is a fine tuned version of openai/whisper medium on the None dataset. It achieves the following results on the evaluation set: Loss: 0.9563 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: 1e 05 train batch size: 16 eval batch size: 8 seed: 42 optimizer: Use OptimizerNames.ADAMW TORCH FUSED with betas=(0.9,0.999) and epsilon=1e 08 and optimizer args=No additional optimizer arguments lr scheduler type: linear lr scheduler warmup steps: 500 training steps: 5000 mixed precision training: Native AMP Training results Training Loss Epoch Step Validation Loss : : : : : : : : 0.5216 1.0546 1000 0.7874 0.1898 2.1092 2000 0.8209 0.0491 4.0184 3000 0.8889 0.0220 5.073 4000 0.9264 0.0051 6.1276 5000 0.9563 Framework versions Transformers 5.6.0.dev0 Pytorch 2.10.0+cu128 Datasets 2.16.0 Tokenizers 0.22.2
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy