Model Card for wav2vec2-large-voxrex-300m-combined-long

This is a wav2vec2 model fined tuned on a Norwegian dataset combining data from the Norwegian parliament proceedings and broadcast news.

Model Details

The model is fined tuned from a Swedish model with 300 million parameters trained by the Swedish Royal Library.

Model Description

Developed by: The SCRIBE project https://scribe-project.github.io/
Shared by: The SCRIBE project https://scribe-project.github.io/
Model type: wav2vec2
Language(s) (NLP): Norwegian
License: Apache 2.0
Finetuned from model: KBLab/wav2vec2-large-voxrex

Model Sources

Repository: https://github.com/scribe-project/nodalida_2023_combined_training

Paper:

@InProceedings{SolbergEtAlNoDaLiDa2023,
author = {Per Erik Solberg and Pablo Ortiz and Phoebe Parsons and Torbjørn Svendsen and Giampiero Salvi},	 
title = {Improving Generalization of Norwegian ASR with Limited Linguistic Resources},
booktitle = {Proceedings of the 24th Nordic Conference on Computational Linguistics},
year = 	 {2023},
month = 	 {May},
address = 	 {Tórshavn, Faroe Islands},
}

Uses

The model can be used for automatic speech recognition in Norwegian, and other tasks involving speech technology

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]