Wav2vec2 Lar Xlsr Finetune Es Col
This model is a fine-tuned Spanish (Colombian accent) speech recognition model based on facebook/wav2vec2-large-xlsr-53, achieving a word error rate (WER) of 0.2595 on the evaluation set.
Downloads 26
Release Time : 3/2/2022
Model Overview
This is an automatic speech recognition (ASR) model optimized for Spanish (Colombian accent), fine-tuned based on the wav2vec2-large-xlsr-53 architecture.
Model Features
Colombian accent optimization
Specifically optimized for the Spanish accent in the Colombian region
Low word error rate
Achieved a word error rate (WER) of 0.2595 on the evaluation set
Based on XLSR architecture
Fine-tuned based on the powerful wav2vec2-large-xlsr-53 architecture
Model Capabilities
Spanish speech-to-text
Colombian accent recognition
Continuous speech recognition
Use Cases
Speech transcription
Meeting minutes
Automatically transcribe Spanish meeting content from Colombia
Accuracy approximately 74% (based on WER 0.2595)
Customer service dialogue analysis
Analyze voice feedback from Colombian customers
Voice assistants
Localized voice assistant
Develop voice assistant applications for the Colombian region
Featured Recommended AI Models
Š 2025AIbase