README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - minds14
metrics:
  - wer
model-index:
  - name: my_asr_model_2
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: minds14
          type: minds14
          config: en-US
          split: train[:100]
          args: en-US
        metrics:
          - name: Wer
            type: wer
            value: 1

my_asr_model_2

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: 3.1785
• 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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0949	20.0	100	3.1923	1.0
3.0836	40.0	200	3.1769	1.0
3.0539	60.0	300	3.1766	1.0
3.0687	80.0	400	3.1853	1.0
3.0649	100.0	500	3.1785	1.0

Framework versions

• Transformers 4.25.1
• Pytorch 1.13.1+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2