Wav2Vec2 Large Wolof

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

• eval_loss: 0.2516
• eval_wer: 22.3681
• eval_runtime: 224.3149
• eval_samples_per_second: 10.008
• eval_steps_per_second: 1.253
• epoch: 13.96
• step: 5500

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: 20

Framework versions

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