new_asr_model

This model is a fine-tuned version of facebook/wav2vec2-large-960h-lv60-self on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0553
• Wer: 0.1515

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: 36
• 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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
7.1498	3.88	500	1.9949	0.9938
0.4835	7.75	1000	0.0690	0.1562
0.1202	11.63	1500	0.0555	0.1513
0.0842	15.5	2000	0.0564	0.1516
0.0637	19.38	2500	0.0559	0.1521
0.0647	23.26	3000	0.0553	0.1515

Framework versions

• Transformers 4.11.3
• Pytorch 1.13.1+cu117
• Datasets 1.14.0
• Tokenizers 0.10.3