model_dialect

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: 0.8038
• Accuracy: 0.7113

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: 4e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
6.4219	0.9455	13	1.5899	0.2610
6.2904	1.9636	27	1.4556	0.4550
5.4442	2.9818	41	1.2566	0.5219
5.0752	4.0	55	1.1670	0.5566
4.748	4.9455	68	1.0790	0.5958
4.2202	5.9636	82	1.0372	0.6120
4.0075	6.9818	96	0.9833	0.6397
3.5847	8.0	110	0.9311	0.6721
3.3304	8.9455	123	0.9242	0.6420
3.2199	9.9636	137	0.8707	0.6928
2.9659	10.9818	151	0.8680	0.6767
2.8954	12.0	165	0.8357	0.6952
2.6402	12.9455	178	0.8325	0.7021
2.4812	13.9636	192	0.8158	0.6998
2.4249	14.9818	206	0.8042	0.7090
2.4249	15.1273	208	0.8038	0.7113

Framework versions

• Transformers 4.46.0
• Pytorch 2.4.0
• Datasets 3.0.1
• Tokenizers 0.20.0