This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 az dataset. It achieves the following results on the evaluation set:

Loss: 0.9435
Wer: 38.4615

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: 8
seed: 42
gradient_accumulation_steps: 4
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: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Epoch	Step	Validation Loss	Wer
999.0	1000	0.8373	39.6450
1999.0	2000	0.9435	38.4615
2999.0	3000	1.0010	43.1953
3999.0	4000	1.0380	44.3787
4999.0	5000	1.0529	43.7870

Framework versions

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

geninhu/whisper-large-v2-az

Whisper Large v2 Azerbaijani

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

geninhu/
whisper-large-v2-az