wav2vec2-1b-Yfreq – AI Model by Gummybear05 | AlphaNeural AI

You can deploy this model and start earning money today!

Gummybear05/
wav2vec2-1b-Yfreq

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-1b

endpoints_compatible

Views

No views yet

wav2vec2-1b-Yfreq

This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9186
Cer: 22.6034

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: 0.0001
train_batch_size: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
9.3629	0.2580	200	4.3299	93.9203
2.2328	0.5160	400	2.2799	48.5315
1.4151	0.7741	600	1.8903	42.5458
1.1295	1.0321	800	1.3289	31.4203
0.9021	1.2901	1000	1.4856	35.1386
0.7875	1.5481	1200	1.2296	29.7639
0.703	1.8062	1400	1.1147	27.4142
0.5742	2.0642	1600	1.3386	32.8830
0.4622	2.3222	1800	1.1969	28.9944
0.4357	2.5802	2000	0.9961	25.4053
0.4243	2.8383	2200	1.0207	25.6520
0.3583	3.0963	2400	0.9670	23.5256
0.2933	3.3543	2600	1.0203	24.9354
0.2761	3.6123	2800	0.9008	22.3978
0.278	3.8703	3000	1.0471	25.8576
0.2653	4.1284	3200	1.0037	24.1130
0.2095	4.3864	3400	0.9796	23.8252
0.202	4.6444	3600	0.9249	22.5211
0.1946	4.9024	3800	0.9186	22.6034

Framework versions

Transformers 4.45.2
Pytorch 2.3.1.post100
Datasets 2.19.1
Tokenizers 0.20.1