wav2vec2-xls-r-300m-swahili-cv-fleurs-alffa-alphabets-phonemes-bookbot

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1492
• Wer: 0.0575
• Cer: 0.0491

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: 0.0002
• 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_ratio: 0.1
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.6145	0.9998	2494	0.2315	0.0814	0.0682
0.4098	2.0	4989	0.1790	0.0674	0.0568
0.2986	2.9994	7482	0.1492	0.0575	0.0491

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.1
• Datasets 2.19.2
• Tokenizers 0.20.1