fineturning-with-pretraining-2

This model is a fine-tuned version of Aviral2412/mini_model on the common_voice_1_0 dataset. It achieves the following results on the evaluation set:

• Loss: 2.6209
• Wer: 1.0047

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: 0.0009
• 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: 500
• num_epochs: 35
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.4746	4.29	500	2.5056	1.0013
2.4704	8.58	1000	2.4840	1.0013
2.4346	12.88	1500	2.4060	1.0013
2.3825	17.17	2000	2.4998	1.0014
2.2596	21.46	2500	2.6122	1.0019
2.1902	25.75	3000	2.6619	1.0027
2.1675	30.04	3500	2.6117	1.0048
2.143	34.33	4000	2.6209	1.0047

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2