wavlm-base – AI Model by cloudwalkerw | AlphaNeural AI

You can deploy this model and start earning money today!

cloudwalkerw/
wavlm-base

like

0

audio-classification

generated_from_trainer

microsoft/wavlm-base

endpoints_compatible

Views

No views yet

wavlm-base

This model is a fine-tuned version of microsoft/wavlm-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3307
Accuracy: 0.8974

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: 8
eval_batch_size: 2
seed: 0
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_ratio: 0.1
num_epochs: 10.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3744	1.0	793	0.3307	0.8974
0.3699	2.0	1586	0.3342	0.8974
0.2898	3.0	2379	0.3341	0.8974
0.3126	4.0	3173	0.3363	0.8974
0.3753	5.0	3966	0.3309	0.8974
0.3617	6.0	4759	0.3325	0.8974
0.3453	7.0	5552	0.3315	0.8974
0.3337	8.0	6346	0.3364	0.8974
0.2829	9.0	7139	0.3327	0.8974
0.3189	10.0	7930	0.3321	0.8974

Framework versions

Transformers 4.34.0.dev0
Pytorch 2.0.0.post302
Datasets 2.14.5
Tokenizers 0.13.3