Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Python asraudiochineseemotion-recognitionfunasrmcp-servermultilingual-asropenai-compatible-apiparaformerpunctuationpytorchreal-time-asrspeaker-diarizationspeech-recognitionspeech-to-textstreaming-asrtranscriptionvllmvoice-activity-detectionwhisper-alternative
{
"rkCsdjBackendUrl": "http://27.17.3.62:20629/rk-czrk-backend",
"rkKstbBackendUrl": "http://27.17.3.62:20626/rk-kstb-backend",
"sysId": "387f1f93-b5cb-46e4-9cb4-29146afa643a",
"axiosDefaultsBaseURL": "http://27.17.3.62:20626/rk-kstb-backend",
"ssoProxyLogoutPathname": "/kstb-nm/#/logout",
"ssoServerLoginUrl": "http://27.17.3.62:20601/sso-orcl/index.html#/nmgsj",
"rkSjdbBackendUrl": "http://27.17.3.62:20628/rk-sjdb-backend",
"kernelSupportBackendUrl": "http://27.17.3.62:20615/kernel-support-backend",
"rkCommonBackendUrl": "http://27.17.3.62:20625/rk-common-backend",
"ssoServerTokenUrl": "http://27.17.3.62:20612/sso-backend/token",
"rkHadoopDownLoadUrl": "http://27.17.3.62:20617/dfs/download",
"ssoServerLogoutUrl": "http://27.17.3.62:20601/sso-orcl/#/logout",
"rkConfigBackendUrl": "http://27.17.3.62:20624/rk-config-backend"
}