xuliu15/English_32r_LoRA_10h

Whisper Small English 1h

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

• Loss: 0.1261

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4354	1.0	360	0.6277
0.3417	2.0	720	0.5204
0.2939	3.0	1080	0.4573
0.097	4.0	1440	0.1347
0.0839	5.0	1800	0.1294
0.0811	6.0	2160	0.1275
0.0884	7.0	2520	0.1268
0.0925	8.0	2880	0.1263
0.0858	9.0	3240	0.1261
0.0805	10.0	3600	0.1261

Framework versions

• PEFT 0.10.0
• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1