Exp W2v2t Sv Se Wavlm S42
E
Exp W2v2t Sv Se Wavlm S42
Developed by jonatasgrosman
A Swedish automatic speech recognition model fine-tuned from microsoft/wavlm-large, suitable for 16kHz sampled audio input.
Downloads 20
Release Time : 7/9/2022
Model Overview
This model is fine-tuned for Swedish (sv-SE) automatic speech recognition (ASR) tasks, based on the WavLM-large architecture and trained using the Common Voice 7.0 dataset.
Model Features
Swedish Speech Recognition
Automatic speech recognition capabilities optimized specifically for Swedish
Based on WavLM-large Architecture
Fine-tuned using the powerful WavLM-large pre-trained model as the foundation
16kHz Sampling Rate Support
Compatible with 16kHz sampled audio input
Model Capabilities
Swedish speech-to-text
Automatic speech recognition
Use Cases
Speech Transcription
Swedish Speech Transcription
Convert Swedish speech content into text
Voice Assistants
Swedish Voice Command Recognition
Used for command recognition in Swedish voice assistant systems
Featured Recommended AI Models