agnivamaiti/jem-whisper-yi-2026-09-04-v3-cont

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

jem-whisper-yi-2026-09-04-v3-cont

This model is a fine-tuned version of Kohn-AI/jem-whisper-yi-2026-09-03-v3-step3488 on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.4537
• —Wer Ortho: 0.3105
• —Wer: 0.2409

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
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 16
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: constantwithwarmup
• —lrschedulerwarmup_ratio: 0.1
• —lrschedulerwarmup_steps: 100
• —num_epochs: 2

Training results

Framework versions

• —Transformers 4.48.1
• —Pytorch 2.4.0
• —Datasets 3.6.0
• —Tokenizers 0.21.4