wav2BertMusic

nacielo/wav2BertMusic

wav2BertMusic 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

218

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 12, 2023
Updated: Aug 12, 2023
SHA: 456ffbb8

Model card

From the Hugging Face model README

wav2BertMusic

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

Loss: 2.1932
Rouge1: 24.6783
Rouge2: 7.4152
Rougel: 18.5063
Rougelsum: 18.4876
Gen Len: 57.47

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
3.9337	1.0	1361	3.0866	33.4529	9.1841	24.0245	24.0402	61.0
2.9007	2.0	2722	2.5830	21.3719	5.1164	17.9298	17.9543	22.0
2.618	3.0	4083	2.3494	28.6972	8.052	21.1856	21.2321	80.0
2.4682	4.0	5444	2.2407	25.5182	7.855	19.118	19.1135	53.54
2.421	5.0	6805	2.1932	24.6783	7.4152	18.5063	18.4876	57.47

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 12, 2023
Updated: Aug 12, 2023