wav2vec2-base-960h-surah-ikhlas-2

This model is a fine-tuned version of facebook/wav2vec2-base-960h on the ikhlas_recitations dataset. It achieves the following results on the evaluation set:

• Loss: 200.5294
• Cer: 1.0

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
256.0458	1.0	169	202.8593	1.0
219.2379	2.0	338	201.3444	1.0
210.5916	3.0	507	201.3578	1.0
225.264	4.0	676	200.1416	1.0
212.1849	5.0	845	200.4807	1.0
219.4672	6.0	1014	200.2161	1.0
208.3995	7.0	1183	201.0033	1.0
204.0175	8.0	1352	200.4828	1.0
205.3868	9.0	1521	201.3106	1.0
218.4874	10.0	1690	200.5294	1.0

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3