hubert2BertMusicTest

nacielo/hubert2BertMusicTest

hubert2BertMusicTest 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

3% of all-time downloads

All-time downloads

228

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 15, 2023
Updated: Aug 15, 2023
SHA: d8a57108

Model card

From the Hugging Face model README

hubert2BertMusicTest

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

Loss: 5.8221
Rouge1: 15.7283
Rouge2: 1.0309
Rougel: 15.2928
Rougelsum: 15.2996
Gen Len: 98.36

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: 1e-06
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
7.9557	1.0	1361	6.9607	17.7604	1.459	16.0128	16.0274	97.63
6.5119	2.0	2722	6.2240	15.1584	0.9606	14.9311	14.9471	100.0
6.103	3.0	4083	5.9626	15.066	0.9708	14.911	14.9342	100.0
5.9857	4.0	5444	5.8541	15.3603	0.9738	15.0075	15.0097	98.69
5.9223	5.0	6805	5.8221	15.7283	1.0309	15.2928	15.2996	98.36

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 15, 2023
Updated: Aug 15, 2023