”streaming-asr“ 的搜索结果

PaddleSpeech 是基于飞桨 PaddlePaddle 的语音方向的开源模型库，用于语音和音频中的各种关键任务的开发，典型的应用包括：语音识别、语音翻译、语音合成等

Korean Streaming ASR(with Denoiser and Conformer CTC)

Streaming ASR and TTS based on FastAPI+ sherpa-onnx

Bi-directional streaming speech-to-text service using Cloud ASRs

ASR (Automatic Speech Recognition) for real-time streamed audio powered by Whisper and tranformers

流式识别近几年论文整理

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

python实现的流式识别

One command to start a streaming ASR server.

OpenAI Whisper ASR Webservice API

FreeSWITCH ASR APP

Cloud-based Automatic Speech Recognition (ASR) platform and a public ASR webservice.

CTC + Tensorflow Example for ASR

Automatic Speech Recognition (ASR) - German

A CRF-based ASR Toolkit

ASR for Chinese Mandarin

FastCGI support for Kaldi ASR

SOVA ASR (Automatic Speech Recognition)

Keras Interface for Kaldi ASR

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

翻译 - 这是Kaldi项目的正式所在地。

transformer for ASR-systerm (via tensorflow2.0)

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model

NeMo text processing for ASR and TTS

Streaming replication for SQLite.

翻译 - SQLite的流式S3复制。

A ruby library for TTS & ASR document preparation

nginx rtmp扩展，让nginx支持rtmp流媒体服务

#计算机科学#A Data Streaming Library for Efficient Neural Network Training

This library provides common speech features for ASR including MFCCs and filterbank energies.