README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - librispeech_asr_dummy
metrics:
  - wer
model-index:
  - name: wav2vec2-base-librispeech
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: librispeech_asr_dummy
          type: librispeech_asr_dummy
          config: clean
          split: None
          args: clean
        metrics:
          - name: Wer
            type: wer
            value: 0.44274809160305345

wav2vec2-base-librispeech

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

• Loss: 0.8630
• Wer: 0.4427

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1000
• num_epochs: 60
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0416	29.41	500	0.8917	0.4275
0.0419	58.82	1000	0.8630	0.4427

Framework versions

• Transformers 4.36.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2