Wav2Vec2-11 Open-Source Speech Recognition Model - Free Deployment for Automatic Speech-to-Text Conversion

Home

Wav2vec2 11

Developed by chrisvinsen

A fine-tuned speech recognition model based on facebook/wav2vec2-base, supporting automatic speech-to-text tasks

Speech Recognition

Transformers

Open Source License:Apache-2.0 #Speech Recognition #Low Word Error Rate #Audio Processing

Downloads 18

Release Time : 5/23/2022

Model Overview

This model is a speech recognition model based on the wav2vec2 architecture, fine-tuned for speech-to-text conversion tasks.

Model Features

Based on wav2vec2 Architecture

Uses Facebook's wav2vec2-base as the foundational architecture, offering excellent speech feature extraction capabilities

Fine-tuned Optimization

Fine-tuned on specific datasets, potentially optimized for particular speech features or domains

Low Word Error Rate

Evaluation results show a word error rate (WER) of 1.0, indicating strong performance

Model Capabilities

Speech Recognition

Automatic Speech-to-Text

Use Cases

Speech Transcription

Meeting Minutes

Automatically convert meeting recordings into text transcripts

Word error rate 1.0

Voice Notes

Convert voice memos into editable text

🚀 wav2vec2-11

This model is a fine - tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.0827
Wer: 1.0

🚀 Quick Start

This section could introduce how to quickly start using the wav2vec2-11 model, but the original document doesn't provide relevant content, so it is skipped.

✨ Features

This section could describe the main features of the wav2vec2-11 model, but the original document doesn't provide relevant content, so it is skipped.

📦 Installation

This section could show the installation steps of the wav2vec2-11 model, but the original document doesn't provide relevant content, so it is skipped.

💻 Usage Examples

This section could provide code examples for using the wav2vec2-11 model, but the original document doesn't provide relevant content, so it is skipped.

📚 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: 24
eval_batch_size: 6
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 400
num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.2589	1.18	200	3.1595	1.0
2.8683	2.35	400	3.1270	1.0
2.8692	3.53	600	3.1041	1.0
2.8577	4.71	800	3.0804	1.0
2.8587	5.88	1000	3.0556	1.0
2.8615	7.06	1200	3.1084	1.0
2.8598	8.24	1400	3.0608	1.0
2.8571	9.41	1600	3.0997	1.0
2.8595	10.59	1800	3.1533	1.0
2.8568	11.76	2000	3.0621	1.0
2.8563	12.94	2200	3.1072	1.0
2.8556	14.12	2400	3.1299	1.0
2.8581	15.29	2600	3.0565	1.0
2.8534	16.47	2800	3.0821	1.0
2.857	17.65	3000	3.0734	1.0
2.8545	18.82	3200	3.1392	1.0
2.8568	20.0	3400	3.0541	1.0
2.8519	21.18	3600	3.0856	1.0
2.8542	22.35	3800	3.1477	1.0
2.8565	23.53	4000	3.0433	1.0
2.8525	24.71	4200	3.0826	1.0
2.8538	25.88	4400	3.0972	1.0
2.857	27.06	4600	3.0762	1.0
2.8523	28.24	4800	3.0828	1.0
2.8526	29.41	5000	3.0827	1.0

Framework versions

Transformers 4.19.2
Pytorch 1.11.0+cu113
Datasets 2.2.2
Tokenizers 0.12.1

🔧 Technical Details

This section could provide more in - depth technical details about the wav2vec2-11 model, but the original document doesn't provide enough content, so it is skipped.

📄 License

The 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