wav2vec2-common_voice-tr-demo Open Source Model - Free Support for Swedish Automatic Speech Recognition

Wav2vec2 Common Voice Tr Demo

Developed by birgermoell

This model is an automatic speech recognition (ASR) model fine-tuned on the COMMON_VOICE SV-SE dataset based on facebook/wav2vec2-large-xlsr-53, supporting Swedish speech recognition.

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Swedish speech recognition #XLSR-53 fine-tuning #Low word error rate

Downloads 17

Release Time : 3/2/2022

Model Overview

This is an automatic speech recognition model for Swedish, based on the wav2vec2 architecture and fine-tuned on the Common Voice dataset, capable of converting Swedish speech to text.

Model Features

Swedish speech recognition

Speech recognition capability specifically optimized for Swedish

Based on wav2vec2 architecture

Uses facebook's wav2vec2-large-xlsr-53 as the base model

Fine-tuned on Common Voice dataset

Fine-tuned on the Common Voice SV-SE dataset

Model Capabilities

Swedish speech-to-text

Automatic speech recognition

Use Cases

Speech transcription

Swedish speech transcription

Convert Swedish speech content into editable text format

Word error rate (WER) of 0.3811

Voice assistant

Swedish voice command recognition

Used for voice command recognition in Swedish voice assistants

Training Loss	Epoch	Step	Validation Loss	Wer
No log	0.74	100	3.4444	1.0
No log	1.47	200	2.9421	1.0
No log	2.21	300	2.2802	1.0137
No log	2.94	400	0.9683	0.7611
3.7264	3.68	500	0.7941	0.6594
3.7264	4.41	600	0.6695	0.5751
3.7264	5.15	700	0.6507	0.5314
3.7264	5.88	800	0.5731	0.4927
3.7264	6.62	900	0.5723	0.4580
0.4592	7.35	1000	0.5913	0.4479
0.4592	8.09	1100	0.5562	0.4423
0.4592	8.82	1200	0.5566	0.4292
0.4592	9.56	1300	0.5492	0.4303
0.4592	10.29	1400	0.5665	0.4331
0.2121	11.03	1500	0.5610	0.4084
0.2121	11.76	1600	0.5703	0.4014
0.2121	12.5	1700	0.5669	0.3898
0.2121	13.24	1800	0.5586	0.3962
0.2121	13.97	1900	0.5656	0.3897
0.1326	14.71	2000	0.5565	0.3813

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご

Wav2vec2 Common Voice Tr Demo

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 wav2vec2-common_voice-tr-demo

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License