wav2vec2-large-voxrex-npsc-bokmaal

NbAiLab/wav2vec2-large-voxrex-npsc-bokmaal

wav2vec2-large-voxrex-npsc-bokmaal is a automatic speech recognition model from NbAiLab. Use it when you need speech turned into text. 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

7% of all-time downloads

All-time downloads

1.1K

Public

Repo size

105 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin5.5 GB · 94%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: Mar 2, 2022
Updated: Mar 24, 2022
SHA: 8671e176

Datasets

NbAiLab/NPSC

Model card

From the Hugging Face model README

wav2vec2-large-voxrex-npsc-bokmaal

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1311
Wer: 0.1038

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: 8.379967082059723e-06
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 0.1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2127	0.32	500	0.1335	0.1047
0.1976	0.64	1000	0.1309	0.1039
0.1887	0.97	1500	0.1306	0.1040
0.18	1.29	2000	0.1311	0.1038

Framework versions

Transformers 4.17.0.dev0
Pytorch 1.10.2+cu113
Datasets 1.18.4.dev0
Tokenizers 0.11.0

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: Mar 2, 2022
Updated: Mar 24, 2022