VladS159/Whisper_small_ro_VladS_6000_steps_multi-gpu_28_05_2024

<!-- 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 Small Ro - Sarbu Vlad - multi gpu --> 3

This model is a fine-tuned version of openai/whisper-small on the Common Voice 17.0 + Romanian speech synthesis dataset. It achieves the following results on the evaluation set:

• —Loss: 0.1249
• —Wer: 10.5571

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: 16
• —evalbatchsize: 10
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 3
• —totaltrainbatch_size: 48
• —totalevalbatch_size: 30
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 600
• —training_steps: 6000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.37.2
• —Pytorch 2.2.0
• —Datasets 2.17.0
• —Tokenizers 0.15.1