Dansk-wav2vec2-stt

Privoid-ai/Dansk-wav2vec2-stt

Dansk-wav2vec2-stt is a automatic speech recognition model from Privoid-ai. 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

3% of all-time downloads

All-time downloads

373

Public

Repo size

3.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.3 GB · 100%

At a glance

Task: Automatic Speech Recognition
Library: transformers
License: apache-2.0
Model type: wav2vec2
Access: Public
Created: May 8, 2022
Updated: May 8, 2022
SHA: 7210bd52

Datasets

common_voice

Model card

From the Hugging Face model README

Dansk-wav2vec2-stt

This model is a fine-tuned version of Siyam/Dansk-wav2vec21 on the common_voice dataset. It achieves the following results on the evaluation set:

Loss: 0.7500
Wer: 0.3929

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: 0.0003
train_batch_size: 16
eval_batch_size: 8
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
lr_scheduler_warmup_steps: 500
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0298	4.26	400	0.8420	0.4579
0.0479	8.51	800	0.8713	0.4461
0.0387	12.77	1200	0.8307	0.4404
0.0336	17.02	1600	0.8322	0.4144
0.0322	21.28	2000	0.7493	0.4081
0.0288	25.53	2400	0.7361	0.3951
0.0264	29.79	2800	0.7500	0.3929

Framework versions

Transformers 4.11.3
Pytorch 1.10.0+cu113
Datasets 2.1.0
Tokenizers 0.10.3

Task: Automatic Speech Recognition
Library: transformers
Type: wav2vec2
License: apache-2.0
Created: May 8, 2022
Updated: May 8, 2022