This model is a fine-tuned version of facebook/w2v-bert-2.0 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

Loss: 1.0297
Wer: 0.9565
Cer: 0.2641

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: 0.001
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.856	1.5385	500	0.9286	0.9535	0.2798
0.7189	3.0769	1000	0.8544	0.9296	0.2557
0.6114	4.6154	1500	0.9302	0.9596	0.2675
0.4397	6.1538	2000	0.9972	0.9294	0.2585
0.4507	7.6923	2500	0.9594	0.9363	0.2589
0.3154	9.2308	3000	1.0297	0.9565	0.2641

Framework versions

Transformers 4.41.2
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

LevonHakobyan/adapter_freezed_base_const_lr_1-e3

adapter_freezed_base_const_lr_1-e3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

LevonHakobyan/
adapter_freezed_base_const_lr_1-e3