English-Filipino Wav2Vec2 Large XLS-R Test 09 Open-Source Model - Achieving Precise Speech Recognition for English and Filipino

English Filipino Wav2vec2 L Xls R Test 09

Developed by Khalsuu

English-Filipino speech recognition model fine-tuned from jonatasgrosman/wav2vec2-large-xlsr-53-english, achieving a WER of 0.5750 on the evaluation set

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Filipino speech recognition #Multilingual transfer learning #Low-resource optimization

Downloads 29.03k

Release Time : 5/8/2022

Model Overview

This model is a speech recognition model based on the wav2vec2-large-xlsr-53 architecture, specifically optimized for mixed English and Filipino speech

Model Features

Multilingual support

Supports mixed English and Filipino speech recognition

Efficient fine-tuning

Achieves good results with limited data through efficient fine-tuning of pre-trained models

Low word error rate

Achieves a word error rate (WER) of 0.5750 on the evaluation set

Model Capabilities

English speech recognition

Filipino speech recognition

Mixed-language speech recognition

Use Cases

Speech transcription

English-Filipino mixed speech transcription

Transcribes speech content containing both English and Filipino into text

Word error rate 0.5750

Voice assistants

Multilingual voice command recognition

Recognizes voice commands in mixed English and Filipino

Training Loss	Epoch	Step	Validation Loss	Wer
3.001	2.09	400	1.3499	0.9595
0.8606	4.19	800	0.8159	0.6942
0.5819	6.28	1200	0.7372	0.6700
0.4751	8.38	1600	0.7310	0.6405
0.3777	10.47	2000	0.7841	0.6414
0.2918	12.57	2400	0.7898	0.5951
0.2209	14.66	2800	0.8558	0.5751
0.1671	16.75	3200	0.9881	0.5979
0.129	18.85	3600	1.0054	0.5750

Property	Details
Model Type	english-filipino-wav2vec2-l-xls-r-test-09
Training Data	filipino_voice

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

English Filipino Wav2vec2 L Xls R Test 09

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 english-filipino-wav2vec2-l-xls-r-test-09

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

🔧 Technical Details

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License