whisper-small-tg

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

• Loss: 0.6917
• Wer: 28.3622

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: 64
• eval_batch_size: 32
• 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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0011	25.0	1000	0.5801	28.1310
0.0004	50.0	2000	0.6423	28.2620
0.0002	75.0	3000	0.6796	28.3931
0.0002	100.0	4000	0.6917	28.3622

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2