working

This model is a fine-tuned version of facebook/wav2vec2-base on the vivos dataset. It achieves the following results on the evaluation set:

• Loss: 0.2735
• Wer: 0.1931

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.8333	1.0274	300	3.7834	1.0
2.3412	2.0548	600	0.8215	0.5481
0.6754	3.0822	900	0.4963	0.3560
0.4809	4.1096	1200	0.3978	0.2980
0.395	5.1370	1500	0.3535	0.2613
0.3453	6.1644	1800	0.3192	0.2318
0.3024	7.1918	2100	0.2948	0.2166
0.2683	8.2192	2400	0.2844	0.2043
0.2468	9.2466	2700	0.2785	0.1947

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1