mikr/whisper-large2-czech-cv11-v2

<!-- 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. -->

Whisper Large-v2 Czech CV11 v2

This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/commonvoice11_0 cs dataset. It achieves the following results on the evaluation set:

• —Loss: 0.2120
• —Wer: 9.0459

Model description

Fine tuned with deepspeed optimization and batch_size: 32.

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: 32
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 64
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 500
• —training_steps: 5000

Training results

Framework versions

• —Transformers 4.26.0.dev0
• —Pytorch 1.13.0+cu117
• —Datasets 2.7.1.dev0
• —Tokenizers 0.13.2