testTrain

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

• Loss: 3.1925
• 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: 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: 1000
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.4277	2.6596	500	3.4397	1.0
3.0899	5.3191	1000	3.3248	1.0
2.986	7.9787	1500	3.1192	1.0
2.9818	10.6383	2000	3.2309	1.0
2.9831	13.2979	2500	3.1589	1.0
2.9814	15.9574	3000	3.1514	1.0
2.9809	18.6170	3500	3.2345	1.0
2.9821	21.2766	4000	3.1681	1.0
2.976	23.9362	4500	3.1974	1.0
2.9812	26.5957	5000	3.1984	1.0
2.9824	29.2553	5500	3.1925	1.0

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.0.post101
• Datasets 2.19.1
• Tokenizers 0.20.1