TheRains/output-base-id

Whisper base ID - Augmented

This model is a fine-tuned version of openai/whisper-base on the mozilla-foundation/common_voice_12_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2277
• Wer: 11.2027

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.5509	0.77	200	0.3243	13.8588
0.3844	1.54	400	0.2590	11.1782
0.259	2.31	600	0.2422	18.6813
0.1608	3.07	800	0.2361	11.6678
0.1205	3.84	1000	0.2277	11.2027

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu117
• Datasets 2.10.1
• Tokenizers 0.13.2