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
update ERROR msg
雾聪652627e6dfea
diff --git a/runtime/websocket/bin/websocket-server-2pass.cpp b/runtime/websocket/bin/websocket-server-2pass.cppindex 954ffae9d..8c8cab419 100644--- a/runtime/websocket/bin/websocket-server-2pass.cpp+++ b/runtime/websocket/bin/websocket-server-2pass.cpp@@ -211,7 +211,7 @@ void WebSocketServer::do_decoder(if(wav_format != "pcm" && wav_format != "PCM"){websocketpp::lib::error_code ec;nlohmann::json jsonresult;- jsonresult["text"] = "ERROR. Real-time transcription service ONLY SUPPORT wav_format pcm.";+ jsonresult["text"] = "ERROR. Real-time transcription service ONLY SUPPORT PCM stream.";jsonresult["wav_name"] = wav_name;jsonresult["is_final"] = true;if (is_ssl) {