The wav2vec2-large-xls-r-300m-irish Open-source Speech Model - Free Deployment for Automatic Irish Language Recognition

Wav2vec2 Large Xls R 300m Irish Colab Test

Developed by jfealko

This is a speech recognition model fine-tuned on the Common Voice Irish dataset based on the facebook/wav2vec2-xls-r-300m model, primarily used for automatic speech recognition tasks in Irish.

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Irish speech recognition #Multilingual speech processing #Low-resource optimization

Downloads 24

Release Time : 4/1/2022

Model Overview

This model is a fine-tuned version of wav2vec2-xls-r-300m, specifically optimized for Irish speech recognition, achieving a 62.2% word error rate on the Common Voice dataset.

Model Features

Irish Language Optimization

Specially fine-tuned and optimized for Irish speech recognition

Based on wav2vec2-xls-r Architecture

Utilizes Facebook's powerful wav2vec2-xls-r-300m architecture as the base model

Medium Scale

300 million parameter model size, balancing performance and efficiency

Model Capabilities

Irish speech recognition

Speech-to-text

Automatic speech transcription

Use Cases

Speech Transcription

Irish Speech Transcription

Convert Irish speech content into text

Word error rate 62.2%

Voice Assistants

Irish Voice Assistant

Used to develop voice assistant applications supporting Irish

🚀 wav2vec2-large-xls-r-300m-irish-colab_test

This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It can achieve specific results on the evaluation set, which helps in speech - related tasks.

🚀 Quick Start

This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:

Loss: 1.7839
Wer: 0.6220

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 90
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
10.0428	2.94	50	4.1311	1.0
3.2917	5.88	100	3.1468	1.0
3.0221	8.82	150	2.9848	1.0
2.9795	11.76	200	2.9567	1.0
2.9379	14.71	250	2.9463	1.0
2.9068	17.65	300	2.8330	1.0
2.5088	20.59	350	1.9807	0.9535
1.6188	23.53	400	1.4254	0.8398
1.0435	26.47	450	1.3668	0.7807
0.7212	29.41	500	1.3914	0.7476
0.5456	32.35	550	1.5495	0.7470
0.4297	35.29	600	1.4751	0.6960
0.3533	38.24	650	1.5157	0.6909
0.2899	41.18	700	1.5394	0.6879
0.2529	44.12	750	1.6186	0.6903
0.2413	47.06	800	1.6386	0.6954
0.2113	50.0	850	1.6906	0.6778
0.1769	52.94	900	1.6918	0.6575
0.1622	55.88	950	1.7313	0.6572
0.1564	58.82	1000	1.7701	0.6510
0.1637	61.76	1050	1.6800	0.6444
0.148	64.71	1100	1.7306	0.6477
0.1385	67.65	1150	1.7605	0.6408
0.1264	70.59	1200	1.7534	0.6244
0.1157	73.53	1250	1.7906	0.6381
0.1027	76.47	1300	1.7803	0.6265
0.1061	79.41	1350	1.7617	0.6259
0.0934	82.35	1400	1.7649	0.6253
0.0904	85.29	1450	1.7713	0.6187
0.0911	88.24	1500	1.7839	0.6220

Framework versions

Transformers 4.11.3
Pytorch 1.10.0+cu111
Datasets 1.18.3
Tokenizers 0.10.3

📄 License

This model is licensed under the Apache - 2.0 license.

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