wav2vec2-large-xlsr-53-AsanteTwi-07

This model is a fine-tuned version of ayertey01/wav2vec2-large-xlsr-53-AsanteTwi-06second on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.8573
• Wer: 0.4375

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0656	16.67	100	0.6553	0.5
0.0354	33.33	200	0.7952	0.5
0.0329	50.0	300	0.6705	0.4375
0.0261	66.67	400	0.7253	0.4375
0.0214	83.33	500	0.8056	0.4375
0.0236	100.0	600	0.8573	0.4375

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.0
• Tokenizers 0.13.3