conformer

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。

T-one is a high-performance streaming ASR pipeline for Russian, specialized for the telephony domain.

An implementation of Conformer: Convolution-augmented Transformer for Speech Recognition, a Transformer Variant in TensorFlow/Keras

A python implementation of “Self-Supervised Learning of Spatial Acoustic Representation with Cross-Channel Signal Reconstruction and Multi-Channel Conformer” [TASLP 2024]

On-device speech-to-text for iOS/macOS powered by NVIDIA NeMo Conformer CTC Small (13M params). Pure Swift + CoreML implementation with automatic audio padding, chunking for long audio, and real-time recognition.

An implementation for "Conformer: Convolution-augmented Transformer for Speech Recognition" Paper

I'm building an end-to-end Vietnamese Speech Recognition System. I'll deploy it into production with the help of Flask, Uwsgi, Nginx, and AWS ...