metadata

library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - minds14
metrics:
  - wer
model-index:
  - name: my_awesome_asr_mind_model
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: minds14
          type: minds14
          config: en-US
          split: None
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 0.9547738693467337

my_awesome_asr_mind_model

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

Loss: 3.2374
Wer: 0.9548

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: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 2000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.6527	200.0	1000	3.5556	0.9749
2.9601	400.0	2000	3.2374	0.9548

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.1