369 Open source projects that are alternatives of or similar to Speecht

language model in Chinese，基于Pytorch官方文档实现

Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing

A fully convolution-network for speech-to-text, built on pytorch.

An implementation of model parallel GPT-3-like models on GPUs, based on the DeepSpeed library. Designed to be able to train models in the hundreds of billions of parameters or larger.

Personalized Query Completion

Deep-Learning Model Exploration and Development for NLP

Electra pre-trained model using Vietnamese corpus

中文预训练XLNet模型: Pre-Trained Chinese XLNet_Large

An implementation of Google Brain's 2019 XLNet in PyTorch

LSTM and QRNN Language Model Toolkit for PyTorch

Multi-label Classification with BERT; Fine Grained Sentiment Analysis from AI challenger

Rust re-implementation of OpenFST - library for constructing, combining, optimizing, and searching weighted finite-state transducers (FSTs). A Python binding is also available.

Source code for "Learning protein sequence embeddings using information from structure" - ICLR 2019

BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)

结合python一起学习自然语言处理 (nlp): 语言模型、HMM、PCFG、Word2vec、完形填空式阅读理解任务、朴素贝叶斯分类器、TFIDF、PCA、SVD

Phonetisaurus G2P

a sklearn wrapper for Google's BERT model

Speech to text (PocketSphinx, Iflytex API, Baidu API) and text to speech (pyttsx3) | 语音转文字（PocketSphinx、百度 API、科大讯飞 API）和文字转语音（pyttsx3）

Optimus: the first large-scale pre-trained VAE language model

Offline speech recognition for Android with Vosk library.

An implementation of model parallel GPT2& GPT3-like models, with the ability to scale up to full GPT3 sizes (and possibly more!), using the mesh-tensorflow library.

Top-k Approximate String Matching.

XLNet for generating language.

Empower Sequence Labeling with Task-Aware Neural Language Model | a PyTorch Tutorial to Sequence Labeling

ASR with PyTorch

A UI component that makes it easy to add voice interaction to your app.

Language Modeling

The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)

Implementation of a seq2seq model for Speech Recognition using the latest version of TensorFlow. Architecture similar to Listen, Attend and Spell.

A library & tools to evaluate predictive language models.

💬 Speech to text, using the awesome engines readily available on the device.

The implementation of DeBERTa

A minimal TF2 re-implementation of the OpenAI GPT training

State of the art Chinese Word Segmentation with Bi-LSTMs

PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

🐍 Python library for n-gram models in ARPA format

An Android app that offers speech-to-text services and user interfaces to other apps

GPT-2 French demo | Démo française de GPT-2

Tensorflow Implementation of Expressive Tacotron

Wave2vec 2.0 Recognize pipeline

Transformer with Untied Positional Encoding (TUPE). Code of paper "Rethinking Positional Encoding in Language Pre-training". Improve existing models like BERT.

an open-source implementation of sequence-to-sequence based speech processing engine

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

VOSK Speech Recognition Toolkit

readers that enable reading kaldi ark in tensorflow

The Naomi Project is an open source, technology agnostic platform for developing always-on, voice-controlled applications!

A TensorFlow Implementation of DC-TTS: yet another text-to-speech model

Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.

Music advice from a conversational interface powered by Algolia

Creating a software for automatic monitoring in online proctoring

A Pytorch implementation for the ZeroSpeech 2019 challenge.

End-to-End Speech Recognition using Neural Networks.

A curated list of pretrained sentence and word embedding models

A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.

Character-based word embeddings model based on RNN for handling real world texts

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Program to benchmark various speech recognition APIs

A Lite Bert For Self-Supervised Learning Language Representations

Docker image and scripts for training finetuned or completely personal Kaldi speech models. Particularly for use with kaldi-active-grammar.