ft_wav2vec2_base_six_1000

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: 1.4818
• Wer: 40.2628
• Cer: 18.6678

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
3.2787	22.73	1000	1.1585	59.3958	25.8494
0.4164	45.45	2000	1.2611	44.7175	20.5846
0.144	68.18	3000	1.3470	42.6865	19.8831
0.0774	90.91	4000	1.4210	41.7307	19.1922
0.05	113.64	5000	1.4818	40.2628	18.6678

Framework versions

• Transformers 4.39.3
• Pytorch 1.12.1+cu116
• Datasets 2.4.0
• Tokenizers 0.15.2