yt-special-batch8

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

• Loss: nan
• Wer: 100.0

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: 4
• 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0	0.17	1000	nan	100.0
0.0	0.34	2000	nan	100.0
0.0	0.52	3000	nan	100.0
0.0	0.69	4000	nan	100.0
0.0	0.86	5000	nan	100.0

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.13.1
• Tokenizers 0.13.3