Shivam098's picture
End of training
ccd273b verified
|
raw
history blame
1.67 kB
metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: ft-wav2vec2-with-minds-asr
    results: []

ft-wav2vec2-with-minds-asr

This model is a fine-tuned version of facebook/wav2vec2-base on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 23.2819
  • 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: 1e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 40
  • training_steps: 80
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
No log 1.6 20 44.9773 1.0
58.0887 3.2 40 23.2819 1.0
30.3126 4.8 60 13.2997 1.0
30.3126 6.4 80 11.9709 1.0

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.0.0
  • Datasets 2.15.0
  • Tokenizers 0.15.0