wav2BertMusicfreeze

nacielo/wav2BertMusicfreeze

wav2BertMusicfreeze is a automatic speech recognition model from nacielo. Use it when you need speech turned into text. It is set up for transformers.

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

Downloads · 30 days

2% of all-time downloads

All-time downloads

217

Public

Repo size

2.3 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin762 MB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
Model type: speech-encoder-decoder
Access: Public
Created: Aug 13, 2023
Updated: Aug 13, 2023
SHA: d92d659b

Model card

From the Hugging Face model README

wav2BertMusicfreeze

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

Loss: 2.3867
Rouge1: 27.1456
Rouge2: 7.625
Rougel: 20.1034
Rougelsum: 20.0485
Gen Len: 46.26

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
5.1626	1.0	1361	3.9917	24.7464	5.7911	18.5211	18.5124	65.15
3.4372	2.0	2722	3.0113	24.0633	5.6872	18.4731	18.4535	40.02
2.9324	3.0	4083	2.6271	32.2681	8.0887	23.541	23.4982	54.76
2.7227	4.0	5444	2.4558	29.1184	6.5853	21.5936	21.5896	48.21
2.6377	5.0	6805	2.3867	27.1456	7.625	20.1034	20.0485	46.26

Framework versions

Transformers 4.31.0
Pytorch 2.0.1+cu117
Datasets 2.14.2
Tokenizers 0.13.3

Task: Automatic Speech Recognition
Library: transformers
Type: speech-encoder-decoder
Created: Aug 13, 2023
Updated: Aug 13, 2023