bond005

transformers

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

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

pytorch-metric-learning

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

pocketsphinx

A small speech recognizer

wikiextractor

A tool for extracting plain text from Wikipedia dumps

python-readability

fast python port of arc90's readability tool, updated to match latest readability.js!

tabnet

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

kenlm

KenLM: Faster and Smaller Language Model Queries

LightAutoML

Fast and customizable framework for automatic ML model creation (AutoML)

ONE-PEACE

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

open_stt

Open STT

bdl-benchmarks

Bayesian Deep Learning Benchmarks

sphinxbase

vosk

VOSK Speech Recognition Toolkit

sednn

deep learning based speech enhancement using keras or pytorch, make it easy to use

sphinxtrain

Acoustic model trainer for CMU Sphinx

rnnmorph

Morphological analyzer for Russian and English languages based on neural networks and dictionary-lookup systems.

russian_g2p

Accentor and transcriptor for Russian language

ru_sentence_tokenizer

A simple and fast rule-based sentence segmentation. Tested on OpenCorpora and SynTagRus datasets.

SentEvalRu

uncertainty_transformers

RuNNE

RuNNE

tf2-deep-ensemble-uncertainty

Tensorflow 2.0 implementation of "Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles" (http://arxiv.org/abs/1612.01474)

sentirueval

Russian sentiment analysis evaluation SentiRuEval-2016

audio_augmentator

A library to make augmented audio (8/16 kHz, mono, WAV PCM) with noises corpora.

speech_audio_separator

Spliting speech WAV PCM files to fragments with use of energy signal minimums (speech pauses).

ShiftsChallenge

Second place ShiftsChallenge Weather track solution