whisper-small-bg

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_13_0 bg dataset. It achieves the following results on the evaluation set:

• Loss: 9.0612
• Wer: 44.6729

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: 32
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• 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
4.9319	6.76	1000	10.0774	73.9892
2.6116	13.51	2000	11.4089	67.0484
0.9607	20.27	3000	11.8266	60.9448
0.3464	27.03	4000	9.9500	52.1213
0.0122	33.78	5000	9.0612	44.6729

Framework versions

• Transformers 4.31.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.13.3