my_awesome_asr_mind_model

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

• Loss: 8.1710
• Wer: 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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
58.3347	1.0	5	30.3906	1.2065
49.6382	2.0	10	30.3906	1.2065
47.2021	3.0	15	26.6334	1.0109
28.9906	4.0	20	22.2268	1.0
28.247	5.0	25	18.9242	1.0
27.9882	6.0	30	15.4867	1.0
22.125	7.0	35	12.5733	1.0
18.5329	8.0	40	10.6346	1.0
14.7859	9.0	45	9.1798	1.0
14.7127	10.0	50	8.1710	1.0

Framework versions

• Transformers 4.34.0
• Pytorch 2.1.0+cu121
• Datasets 2.14.5
• Tokenizers 0.14.1