SpeechGPT

This model is a fine-tuned version of openai/whisper-small on the librispeech_asr dataset. It achieves the following results on the evaluation set:

• Loss: 0.0813
• Wer: 2.8093

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0956	0.12	1000	0.1065	3.6519
0.1002	0.24	2000	0.0997	3.5453
0.0841	0.36	3000	0.0941	3.3057
0.0839	0.48	4000	0.0905	3.1783
0.0821	0.6	5000	0.0855	2.9595
0.0626	0.72	6000	0.0839	2.9310
0.0643	0.84	7000	0.0821	2.8112
0.0908	0.97	8000	0.0813	2.8093

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2