config-1

This model is a fine-tuned version of DrishtiSharma/wav2vec2-large-xls-r-300m-hi-CV7 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.3415
• Wer: 0.9997
• Cer: 0.9398
• Mer: 0.9997

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_steps: 100
• num_epochs: 40
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Mer
9.6228	1.0050	100	3.5667	1.0	1.0	1.0
3.4908	2.0101	200	3.4348	0.9999	0.9755	0.9999
3.3938	3.0151	300	3.3869	1.0	0.9351	1.0
3.3501	4.0201	400	3.3415	0.9997	0.9398	0.9997

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1