whisper-small-en-v3

This model is a fine-tuned version of noeinatha/whisper-small-en-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.8348
• Wer: 86.0135

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: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	2.31	1000	1.8307	49.0292
0.0	4.63	2000	1.8360	65.7005
0.0	6.94	3000	1.8356	82.1213
0.0	9.26	4000	1.8348	86.0135

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu117
• Datasets 2.11.0
• Tokenizers 0.13.3