649 Open source projects that are alternatives of or similar to rustfst

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

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

The official repository of the Eesen project

Some simple wrappers around kaldi-asr intended to make using kaldi's (online) decoders as convenient as possible.

Port of the OpenFST library to Windows

ASR with PyTorch

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

WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries

Проект для распознавания речи на русском языке на основе pykaldi.

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.

scripts to align a given wave to its transcription using trained models by Kaldi

💻Speech and Natural Language Processing (SLP & NLP) Lab Assignments for ECE NTUA

A Python wrapper for Kaldi

Kaldi-based Korean ASR (한국어 음성인식) open-source project

No description or website provided.

Long audio alignment using Kaldi

Offline speech recognition for Android with Vosk library.

Open tools and data for cloudless automatic speech recognition

💬 An On-Premises, Streaming Speech Recognition System

SincNet is a neural architecture for efficiently processing raw audio samples.

Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

Program to benchmark various speech recognition APIs

Syn.Speech is a flexible speaker independent continuous speech recognition engine for Mono and .NET framework

Speech Recognition model based off of FAIR research paper built using Pytorch.

Mongolian speech recognition with PyTorch

Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.

PyTorch Implementations for End-to-End Automatic Speech Recognition

End-to-end speech recognition on AISHELL dataset.

PyTorch implementation of the Factorized TDNN (TDNN-F) from "Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks" and Kaldi

MXNet implementation of RNN Transducer (Graves 2012): Sequence Transduction with Recurrent Neural Networks

kaldi-asr/kaldi is the official location of the Kaldi project.

A list of publically available audio data that anyone can download for ASR or other speech activities

Production First and Production Ready End-to-End Speech Recognition Toolkit

A pytorch based end2end speech recognition system.

the open-source virtual assistant for Ubuntu based Linux distributions

Automatically constructing corpus for automatic speech recognition from YouTube videos

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

DELTA is a deep learning based natural language and speech processing platform.

Computes the GMM-based Goodness of Pronunciation (GOP). Bases on Kaldi.

A Chinese Deep Speech Recognition System 包括基于深度学习的声学模型和基于深度学习的语言模型

Silero Models: pre-trained STT models and benchmarks made embarrassingly simple

Open-Source Toolkit for End-to-End Korean Automatic Speech Recognition.

Python module for evaluating ASR hypotheses (e.g. word error rate, word recognition rate).

End-to-End Automatic Speech Recognition on PyTorch

Kaldi model converter to ONNX

Python Kaldi speech recognition with grammars that can be set active/inactive dynamically at decode-time

Lingvo

An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.

Chinese text normalization for speech processing

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

End-to-end trained speech recognition system, based on RNNs and the connectionist temporal classification (CTC) cost function.

Working online speech recognition based on RNN Transducer. ( Trained model release available in release )

"A collection of functional programming libraries that can be composed together. Unlike a framework, thi.ng is a suite of instruments and you (the user) must be the composer of. Geared towards versatility, not any specific type of music." — @loganpowell via Twitter

Presenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.

On-device speech-to-text engine powered by deep learning

A merged version of multiple open-source German speech datasets.

A live speech recognition using Facebooks wav2vec 2.0 model.

A list of publically available audio data that anyone can download for ASR or other speech activities

24-hour Automatic Speech Recognition

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