AIbase
EN
Home
Wav2vec2 Large Xlsr Thai Tokenized
W

Wav2vec2 Large Xlsr Thai Tokenized

Developed by chompk
This is a Thai automatic speech recognition (ASR) model based on the Wav2Vec2-Large-XLSR-53 architecture, fine-tuned using the Common Voice dataset and trained with the deepcut tokenizer.
Speech Recognition OtherOpen Source License:Apache-2.0#Thai speech recognition#XLSR fine-tuning#deepcut tokenization
Downloads 44
Release Time : 3/2/2022

Model Overview

This model specializes in Thai speech recognition tasks, capable of converting Thai speech into text. Suitable for applications requiring Thai speech-to-text conversion.

Model Features

Based on XLSR-53 Architecture
Utilizes the Wav2Vec2-Large-XLSR-53 architecture, which excels in cross-lingual speech recognition tasks.
Uses deepcut Tokenizer
Specifically trained with the deepcut tokenizer for Thai language characteristics, optimizing Thai text processing capabilities.
Fine-tuned with Common Voice Dataset
Fine-tuned using the Thai Common Voice dataset, enhancing recognition accuracy for real-world speech.

Model Capabilities

Thai speech recognition
Speech-to-text
Thai speech processing

Use Cases

Speech Transcription
Thai Meeting Minutes
Automatically convert Thai meeting recordings into written transcripts
Thai Voice Assistant
Provide speech recognition capabilities for Thai voice assistants
Education
Thai Learning Applications
Help Thai language learners improve pronunciation through speech practice
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase