README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base-960h
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - wer
model-index:
  - name: wav2vec2-base-self-331-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: test
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 0.98989898989899

wav2vec2-base-self-331-colab

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 2.5154
• Wer: 0.9899

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.3029	30.77	200	3.5530	1.0
3.3121	61.54	400	3.0604	1.0
2.7461	92.31	600	2.5154	0.9899

Framework versions

• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2