Fine_tune_whisper_small

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8238
• Wer: 42.9362

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: 16
• 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: 200
• training_steps: 900
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2994	3.92	200	0.6607	44.0797
0.0201	7.84	400	0.7371	42.6042
0.002	11.76	600	0.8027	42.5304
0.0011	15.69	800	0.8238	42.9362

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2