Speech Recognition for Uyghur using Speech transformer

Last update: Nov 17, 2022

Overview

Speech Recognition for Uyghur using Speech transformer

Training:

this model using CTC loss and Cross Entropy loss for training.

unzip results.7z and thuyg20_data.7z to the same folder where python source files located. then run:

python train.py

Recognition:

for recognition download only pretrained model. then run:

python .\tonu.py .\test6.wav

result will be:

        Model loaded: results/UFormer_last.pth
            Best CER: 4.16%
             Trained: 276 epochs
The model has 36,418,306 trainable parameters
 Feature  has 25,869,058 trainable parameters
  Encoder has 4,205,568 trainable parameters
  Decoder has 6,343,680 trainable parameters

======================
Recognizing file .\test6.wav
test6.wav -> u qizlarning resimi chiqip qalsa bilekchila sinchilap qaraytti

This project using

A free Uyghur speech database Released by [email protected] University & Xinjiang University

Reference

https://github.com/gentaiscool/end2end-asr-pytorch

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

The PyTorch-Kaldi Speech Recognition Toolkit PyTorch-Kaldi is an open-source repository for developing state-of-the-art DNN/HMM speech recognition sys

2.3k Dec 27, 2022

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

Espresso Espresso is an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning libra

919 Jan 3, 2023

Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.

Lightning ASR Modular and extensible speech recognition library leveraging pytorch-lightning and hydra What is Lightning ASR • Installation • Get Star

40 Sep 19, 2022

voice2json is a collection of command-line tools for offline speech/intent recognition on Linux

Command-line tools for speech and intent recognition on Linux

988 Jan 4, 2023

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

26 Dec 14, 2022

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

86 Jun 11, 2021

A fast and lightweight python-based CTC beam search decoder for speech recognition.

pyctcdecode A fast and feature-rich CTC beam search decoder for speech recognition written in Python, providing n-gram (kenlm) language model support

315 Dec 21, 2022

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

🤗 Contributing to OpenSpeech 🤗 OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform ta

513 Jan 3, 2023

ExKaldi-RT: An Online Speech Recognition Extension Toolkit of Kaldi

ExKaldi-RT is an online ASR toolkit for Python language. It reads realtime streaming audio and do online feature extraction, probability computation, and online decoding.

31 Aug 16, 2021

Comments

W2Llayer

Dear Gheyret, Thanks for your work.

I spent some time today to try to figure out the source of this feature extraction layer, can you point me the paper/any reference on it?

I think it is a great design to extract speech features, so just want to understand it more deeply,

Thanks a lot,

Kelvin

opened by kelvinqin 2

Releases(premodel)

premodel(Jun 18, 2021)

Pretrained model.
Source code(tar.gz)
Source code(zip)
results.7z(131.19 MB)

Owner

Uyghur

GitHub Repository

Application for shadowing Chinese.

chinese-shadowing Simple APP for shadowing chinese. With this application, it is very easy to record yourself, play the sound recorded and listen to s

5 Sep 06, 2022

This project aims to conduct a text information retrieval and text mining on medical research publication regarding Covid19 - treatments and vaccinations.

Project: Text Analysis - This project aims to conduct a text information retrieval and text mining on medical research publication regarding Covid19 -

1 Mar 14, 2022

Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5

NLP-Summarizer Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5 This project aimed to provide in

1 Feb 07, 2022

Trains an OpenNMT PyTorch model and SentencePiece tokenizer.

Trains an OpenNMT PyTorch model and SentencePiece tokenizer. Designed for use with Argos Translate and LibreTranslate.

61 Dec 13, 2022

Codes to pre-train Japanese T5 models

t5-japanese Codes to pre-train a T5 (Text-to-Text Transfer Transformer) model pre-trained on Japanese web texts. The model is available at https://hug

37 Dec 25, 2022

iBOT: Image BERT Pre-Training with Online Tokenizer

Image BERT Pre-Training with iBOT Official PyTorch implementation and pretrained models for paper iBOT: Image BERT Pre-Training with Online Tokenizer.

435 Jan 06, 2023

A simple implementation of N-gram language model.

About A simple implementation of N-gram language model. Requirements numpy Data preparation Corpus Training data for the N-gram model, a text file lik

4 Nov 24, 2021

Unsupervised text tokenizer focused on computational efficiency

YouTokenToMe YouTokenToMe is an unsupervised text tokenizer focused on computational efficiency. It currently implements fast Byte Pair Encoding (BPE)

847 Dec 19, 2022

2021语言与智能技术竞赛：机器阅读理解任务

LICS2021 MRC 1. 项目&任务介绍本项目基于官方给定的baseline（DuReader-Checklist-BASELINE）进行二次改造，对整个代码框架做了简单的重构，对核心网络结构添加了注释，解耦了数据读取的模块，并添加了阈值确认的功能，一些小的细节也做了改进。本次任务为202

29 Dec 05, 2022

CCF BDCI 2020 房产行业聊天问答匹配赛道 A榜47/2985

CCF BDCI 2020 房产行业聊天问答匹配 A榜47/2985 赛题描述详见：https://www.datafountain.cn/competitions/474 文件说明 data: 存放训练数据和测试数据以及预处理代码 model_bert.py: 网络模型结构定义 adv_train

40 Sep 28, 2022

BMInf (Big Model Inference) is a low-resource inference package for large-scale pretrained language models (PLMs).

377 Jan 02, 2023

The ability of computer software to identify words and phrases in spoken language and convert them to human-readable text

speech-recognition-py Speech recognition is the ability of computer software to identify words and phrases in spoken language and convert them to huma

1 Apr 03, 2022

A Non-Autoregressive Transformer based TTS, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS.

A Non-Autoregressive Transformer based TTS, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to ach

237 Jan 02, 2023

Speech Recognition for Uyghur using Speech transformer

Related tags

Overview

Speech Recognition for Uyghur using Speech transformer

Training:

Recognition:

This project using

Reference

You might also like...

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

Modular and extensible speech recognition library leveraging pytorch-lightning and hydra.

voice2json is a collection of command-line tools for offline speech/intent recognition on Linux

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

A fast and lightweight python-based CTC beam search decoder for speech recognition.

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

ExKaldi-RT: An Online Speech Recognition Extension Toolkit of Kaldi

Comments

W2Llayer

Releases(premodel)

premodel(Jun 18, 2021)

Owner

Uyghur

Application for shadowing Chinese.

This project aims to conduct a text information retrieval and text mining on medical research publication regarding Covid19 - treatments and vaccinations.

Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5

Trains an OpenNMT PyTorch model and SentencePiece tokenizer.

Codes to pre-train Japanese T5 models

iBOT: Image BERT Pre-Training with Online Tokenizer

A simple implementation of N-gram language model.

Unsupervised text tokenizer focused on computational efficiency

2021语言与智能技术竞赛：机器阅读理解任务

CCF BDCI 2020 房产行业聊天问答匹配赛道 A榜47/2985

BMInf (Big Model Inference) is a low-resource inference package for large-scale pretrained language models (PLMs).

The ability of computer software to identify words and phrases in spoken language and convert them to human-readable text

Implementation of some unbalanced loss like focal_loss, dice_loss, DSC Loss, GHM Loss et.al

Text editor on python to convert english text to malayalam(Romanization/Transiteration).

File-based TF-IDF: Calculates keywords in a document, using a word corpus.

Using BERT-based models for toxic span detection

An Explainable Leaderboard for NLP

Russian words synonyms and antonyms

Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.

A Non-Autoregressive Transformer based TTS, supporting a family of SOTA transformers with supervised and unsupervised duration modelings. This project grows with the research community, aiming to achieve the ultimate TTS.