arnepeine/mona_speech

Mona Speech Model (Trained on ICU Data)

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

• Loss: 0.6949
• Wer: 114.5294

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0001	31.25	1000	0.6152	109.7314
0.0001	62.5	2000	0.6619	111.6657
0.0	93.75	3000	0.6838	114.1096
0.0	125.0	4000	0.6949	114.5294

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2