wav2vec2-phenome-based-alffaamharic

This model is a fine-tuned version of Samuael/wav2vec2-phenome-based-alffaamharic on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.4573
• eval_wer: 0.3543
• eval_runtime: 22.2304
• eval_samples_per_second: 16.149
• eval_steps_per_second: 2.024
• epoch: 11.7
• step: 2200

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: 3e-05
• 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 4.34.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1