This model is a fine-tuned version of openai/whisper-large-v3 on the fsicoli/common_voice_18_0 pt dataset. It achieves the following results on the evaluation set:

Loss: 0.1501
Wer: 0.1074

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: 1000
num_epochs: 10.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1388	0.9996	691	0.1501	0.1074
0.108	1.9993	1382	0.1619	0.1153
0.091	2.9989	2073	0.1697	0.1124
0.0461	4.0	2765	0.1764	0.1120
0.0264	4.9996	3456	0.2024	0.1133
0.0203	5.9993	4147	0.2200	0.1099
0.0129	6.9989	4838	0.2277	0.1114
0.0091	8.0	5530	0.2552	0.1067
0.0063	8.9996	6221	0.2565	0.1054
0.0019	9.9964	6910	0.2671	0.1042

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0+cu124
Datasets 2.18.1.dev0
Tokenizers 0.19.1

fsicoli/whisper-large-v3-pt-3000h-3

whisper-large-v3-pt-3000h-3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

fsicoli/
whisper-large-v3-pt-3000h-3