wav2vec-base-wolof / README.md
serge-wilson's picture
End of training
14b389d
metadata
language:
  - multilingual
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
datasets:
  - serge-wilson/wolof_speech_transcription
model-index:
  - name: Wav2Vec2 Base Wolof
    results: []

Wav2Vec2 Base Wolof

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

  • eval_loss: 0.2953
  • eval_wer: 0.3067
  • eval_runtime: 153.1594
  • eval_samples_per_second: 14.658
  • eval_steps_per_second: 1.835
  • epoch: 15.23
  • step: 6000

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: 32
  • 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: 30

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.0
  • Datasets 2.14.5
  • Tokenizers 0.14.0