asr-afmaay-wav2vec2 – AI Model by ayaazlion | AlphaNeural AI

You can deploy this model and start earning money today!

ayaazlion/
asr-afmaay-wav2vec2

like

0

automatic-speech-recognition

generated_from_trainer

facebook/wav2vec2-xls-r-300m

endpoints_compatible

Views

No views yet

asr-afmaay-wav2vec2

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:

Wer: 0.5950

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: 0.0003
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: linear
lr_scheduler_warmup_steps: 500
num_epochs: 56

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
5.6522	3.65	400	inf	0.9355
1.0451	7.31	800	inf	0.7379
0.7211	10.96	1200	inf	0.7056
0.5122	14.61	1600	inf	0.6823
0.3891	18.26	2000	inf	0.6832
0.2934	21.92	2400	inf	0.6586
0.2379	25.57	2800	inf	0.6384
0.1926	29.22	3200	inf	0.6492
0.1592	32.88	3600	inf	0.6353
0.1328	36.53	4000	inf	0.6411
0.1106	40.18	4400	inf	0.6169
0.0851	43.84	4800	inf	0.6102
0.0702	47.49	5200	inf	0.6098
0.0609	51.14	5600	inf	0.6022
0.0501	54.79	6000	inf	0.5950

Framework versions

Transformers 4.33.1
Pytorch 2.1.2
Datasets 2.19.2
Tokenizers 0.13.3