aalniak's picture
End of training
c1474b3
metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: my_awesome_asr_mind_model
    results: []

my_awesome_asr_mind_model

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 7.9395
  • Wer: 1.0

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: 0.0001
  • train_batch_size: 2
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 10

Training results

Training Loss Epoch Step Validation Loss Wer
No log 0.17 2 9.0543 1.0
No log 0.33 4 8.9431 1.0
No log 0.5 6 9.4171 1.0
No log 0.67 8 8.0264 1.0
No log 0.83 10 7.9395 1.0

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1+cpu
  • Datasets 2.15.0
  • Tokenizers 0.15.0