revised_ft_wav2vec2_base_six_500

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: 2.9206
• Wer: 100.0
• Cer: 99.9853

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
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
4.2117	11.3636	500	2.9404	100.0	99.9283
2.4735	22.7273	1000	1.3017	66.1384	30.0075
0.6303	34.0909	1500	1.1357	49.3524	22.2609
0.2796	45.4545	2000	1.2368	45.0409	21.3033

Framework versions

• Transformers 4.40.1
• Pytorch 1.12.1+cu116
• Datasets 2.19.0
• Tokenizers 0.19.1