The open-source speech recognition model english - filipino - wav2vec2 - l - xls - r - test - 02 enables free English-Filipino bilingual speech-to-text conversion.

English Filipino Wav2vec2 L Xls R Test 02

Developed by Khalsuu

This is a speech recognition model fine-tuned on Filipino speech datasets based on the wav2vec2-large-xlsr-53-english model, supporting English and Filipino speech-to-text tasks.

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Filipino speech recognition #Multilingual speech transcription #Low-resource language model

Downloads 21

Release Time : 5/5/2022

Model Overview

This model is an automatic speech recognition (ASR) system optimized for English and Filipino, based on Facebook's wav2vec2 architecture and fine-tuned on Filipino speech datasets.

Model Features

Multilingual Support

Supports speech recognition for both English and Filipino

Efficient Fine-tuning

Fine-tuned based on a pre-trained large-scale model, achieving good performance with limited data

Low Word Error Rate

Achieved a word error rate (WER) of 26.32% on the evaluation set

Model Capabilities

English speech recognition

Filipino speech recognition

Speech-to-text

Use Cases

Speech Transcription

Filipino Speech Transcription

Convert Filipino speech content into text

Word error rate 26.32%

English Speech Transcription

Convert English speech content into text

Voice Assistants

Multilingual Voice Assistant

Supports voice interaction in both English and Filipino

Training Loss	Epoch	Step	Validation Loss	Wer
3.1707	2.09	400	0.8006	0.8224
0.4801	4.19	800	0.3363	0.4329
0.2541	6.28	1200	0.3365	0.3676
0.1851	8.38	1600	0.3485	0.3739
0.1408	10.47	2000	0.3628	0.3420
0.1098	12.57	2400	0.3979	0.3277
0.1019	14.66	2800	0.4031	0.2896
0.0887	16.75	3200	0.3977	0.3024
0.0798	18.85	3600	0.3959	0.3129
0.0671	20.94	4000	0.4489	0.3241
0.0633	23.04	4400	0.4455	0.3026
0.055	25.13	4800	0.4668	0.2910
0.0523	27.23	5200	0.4670	0.2960
0.0468	29.32	5600	0.4536	0.2781
0.0392	31.41	6000	0.4612	0.2860
0.0381	33.51	6400	0.4651	0.2841
0.034	35.6	6800	0.4723	0.2716
0.0315	37.7	7200	0.4546	0.2642
0.0294	39.79	7600	0.4561	0.2632

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 02

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 english-filipino-wav2vec2-l-xls-r-test-02

🚀 Quick Start

📚 Documentation

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

📄 License