metadata

base_model: NbAiLab/nb-whisper-small-verbatim
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: nb-whisper-small-karelian-CodeSwitching
    results: []

nb-whisper-small-karelian-CodeSwitching

This model is a fine-tuned version of NbAiLab/nb-whisper-small-verbatim on the None dataset. It achieves the following results on the evaluation set:

eval_loss: 55.25
eval_wer: 1.0
eval_cer: 11.0447
eval_runtime: 86.5964
eval_samples_per_second: 4.966
eval_steps_per_second: 0.162
epoch: 0.4535
step: 100

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: 0.007
train_batch_size: 32
eval_batch_size: 32
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 1000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.41.2
Pytorch 2.3.1+cu121
Datasets 2.20.0
Tokenizers 0.19.1