wav2vec2-base-finetuned-ks

AdamAbate1/wav2vec2-base-finetuned-ks

wav2vec2-base-finetuned-ks is a audio classification model from AdamAbate1. Use it for the audio classification task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

1% of all-time downloads

All-time downloads

560

Public

Repo size

2.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin378 MB · 100%

At a glance

Task: Audio Classification
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Aug 6, 2022
Updated: Aug 7, 2022
SHA: 3cbb6222

Datasets

superb

Model card

From the Hugging Face model README

wav2vec2-base-finetuned-ks

This model is a fine-tuned version of facebook/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:

Loss: 0.0993
Accuracy: 0.9812

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: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7367	1.0	399	0.6341	0.8819
0.3087	2.0	798	0.1900	0.9771
0.1979	3.0	1197	0.1232	0.9800
0.171	4.0	1596	0.1057	0.9794
0.1253	5.0	1995	0.0993	0.9812

Framework versions

Transformers 4.21.1
Pytorch 1.12.0
Datasets 2.4.0
Tokenizers 0.12.1

Task: Audio Classification
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: Aug 6, 2022
Updated: Aug 7, 2022